Pith. sign in

Paper Citation Record · LEDGER

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them

As of 8 August 2026, this Paper Citation Record lists 100 of 126 outbound references and 5 inbound Pith citation observations for arXiv:2507.21017.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2507.21017 v1

Coverage vector

measured 100 of 126 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T13:06:45.612718Z

measured 105 of 105 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T04:47:03.693039Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-06-30T15:44:48.487686Z

Reference resolution

100 of 126 outbound references displayed

  • verified exact0
  • verified fuzzy16
  • unresolved84
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bad9f030-7f6f-4408-b8b6-43f9710d4451 · outbound

This paper cites Digirl: Training in-the-wild device-control agents with autonomous reinforcement learning.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Digirl: Training in-the-wild device-control agents with autonomous reinforcement learning

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:36.588726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:36.588726Z digest=sha256:044d220c5b842955f667031247fa8dd3819659563fdebc185c654afd5211333a

Observation c3bc9cd2-4707-482c-8568-42007d7edf06 · outbound

This paper cites HalluLens: LLM Hallucination Benchmark.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them HalluLens: LLM Hallucination Benchmark

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:36.599018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:36.599018Z digest=sha256:f533d383f20bdebfad77ef2ba3dfde045f830d30c6d8eb189be2ce42190c21cb

Observation 4230958e-ec64-4b07-9e13-1ffbebfe9806 · outbound

This paper cites Workarena++: Towards compositional planning and reasoning-based common knowledge work tasks.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Workarena++: Towards compositional planning and reasoning-based common knowledge work tasks

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:36.643937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:36.643937Z digest=sha256:c0249f95b817f5c26cd41433a2ded4d971b8327253f56d4ec06a5bc9b7f2a804

Observation 54f91bce-783f-4b4f-87e5-bb724c73f399 · outbound

This paper cites The BrowserGym Ecosystem for Web Agent Research.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them The BrowserGym Ecosystem for Web Agent Research

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:36.680376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:36.680376Z digest=sha256:7dbc6db02cc0a86e015621280190e344304451aa8bf753e2f8294b90dcbd332e

Observation 18db868a-18b6-4399-982d-7fa4d022729a · outbound

This paper cites Mind2web: Towards a generalist agent for the web.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Mind2web: Towards a generalist agent for the web

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:36.758561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:36.758561Z digest=sha256:432b22dda067d04e118c6e17df635911594cb578a587d2d0ee3339861f0ff8ba

Observation 0c278051-78d7-4b1e-9b9e-ac93a8939375 · outbound

This paper cites WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:36.862403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:36.862403Z digest=sha256:8193de12de3cc65ef4146baa474c6a55d5545745c3269f9df6c59c77f3065a4a

Observation 1dc67f8a-badc-44b3-ad3e-7941ecd1c4b8 · outbound

This paper cites Detecting hallucinations in large language models using semantic entropy.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Detecting hallucinations in large language models using semantic entropy

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:36.962272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:36.962272Z digest=sha256:3c894a3134c84a5c8dc88da76154a0a8749f91fbaef034805485f6c7dc15c6dc

Observation 6c745b19-7cc7-4e3a-952d-688f666634af · outbound

This paper cites Assessment and mitigation of inconsistencies in llm-based evalua- tions.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Assessment and mitigation of inconsistencies in llm-based evalua- tions

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.112150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.112150Z digest=sha256:02559b64017a5737a9a5505592212902ae6e09d8f28951e1e1f240ab0e943c18

Observation 4b3e2150-9332-4955-96f9-f0e321589c62 · outbound

This paper cites A Survey on LLM-as-a-Judge.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them A Survey on LLM-as-a-Judge

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.190014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.190014Z digest=sha256:027622fd025d9b55351a6c4156704c50a287c55093cd7fb05623c5d69f623f0b

Observation 36b476a0-4cf6-4403-b42e-5c0caf4189a5 · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.305624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.305624Z digest=sha256:34121654bd836619610594c4ea7dc6e629243dced74acdc278186f88d34a7513

Observation 0db7d40c-0bf8-420c-b7f5-20b384fa0c21 · outbound

This paper cites Survey of hallucination in natural language generation.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Survey of hallucination in natural language generation

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.388156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.388156Z digest=sha256:3bee2d51b10dabc98ee64acc22c3d9973df4bcb9da6c81956e2bb844c8a224eb

Observation 14d86613-c644-4c26-ac22-beebbf707150 · outbound

This paper cites SWE-bench: Can Language Models Resolve Real-World GitHub Issues?.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.514743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.514743Z digest=sha256:924bf966ec3aa5d3c5ab89b65bb3d7ec457719057855a9efc1e6169f2f708704

Observation 854b0e02-50a3-427d-b778-9b08f4113e17 · outbound

This paper cites The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.580196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.580196Z digest=sha256:73e5f385e88b8cdfbc1274d9712fac2b33d84b6df74ccea019544c28f3add3e0

Observation 207384d8-cd31-49d7-a28f-6a0b39a468c4 · outbound

This paper cites Embodied agent interface: Benchmarking llms for embodied decision making.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Embodied agent interface: Benchmarking llms for embodied decision making

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.650664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.650664Z digest=sha256:8273da4c53ae9e3d743161d0d75c9d5af6906cea0c8a0d3260307b0262b1428d

Observation cb9a1d5a-30e5-432c-b9b6-b8b629e9035e · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.722830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.722830Z digest=sha256:8046d32880e67be5188228494673fbeff1983474cdfb58d5332713192507a3c3

Observation d4524c20-ccdb-4248-bfa1-21d22cba0123 · outbound

This paper cites AgentBench: Evaluating LLMs as Agents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them AgentBench: Evaluating LLMs as Agents

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.802075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.802075Z digest=sha256:ab979d9ef9838e387f7c8cd7cb1e129bfd2cbecb817db0db20a5d00e07affd4d

Observation 2aeec24a-f052-4758-9046-c2ba8d3dba97 · outbound

This paper cites Weblinx: Real-world website navigation with multi-turn dialogue.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Weblinx: Real-world website navigation with multi-turn dialogue

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.903774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.903774Z digest=sha256:90f94c16f548d491bcf2354c9201e24a6cab01453fb1921ab1fbd42b709d622e

Observation 10dd5baf-7564-4263-9296-dde44e02ac82 · outbound

This paper cites HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:37.984774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:37.984774Z digest=sha256:0d19572233aa1510f9f4537f0999b60f5ef3042a459cd3544cf6a793b7bf44de

Observation 8c85bdb2-6dc5-4042-8abe-5185dd740d17 · outbound

This paper cites Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.087768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.087768Z digest=sha256:f34356c62e0aa16f54b5005ebfd7baff8a44bbbe3a570a6b79ce212c1cbff607

Observation 625259ec-4d31-4a5a-b7f0-827a6629c2d5 · outbound

This paper cites FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.175727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.175727Z digest=sha256:1b6661dd540e7ae818d478a84956c97673094d202934cfab5315477359d8e5ad

Observation ed4adeaf-ad9d-4eca-8c71-cb51b2e97a56 · outbound

This paper cites Towards LLMs Robustness to Changes in Prompt Format Styles.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Towards LLMs Robustness to Changes in Prompt Format Styles

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.257775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.257775Z digest=sha256:56446ea1813cab418d9e72ade8684567c04f1283debd52d4a1a890108e1f0672

Observation 9a4f8bc8-07fc-4e45-a27c-04f584ef4ef8 · outbound

This paper cites RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.332252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.332252Z digest=sha256:805e3db51ed9aa334fcff25142b4d33cfb5914770990938d82757471fef9f857

Observation 76d298b1-746d-4208-bed2-341bfa53cc59 · outbound

This paper cites HALoGEN: Fantastic LLM Hallucinations and Where to Find Them.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them HALoGEN: Fantastic LLM Hallucinations and Where to Find Them

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.445916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.445916Z digest=sha256:c49b12f8e529e308eb1c219a93383c12e7b700a9721d908d6c6a8d96563af958

Observation acbcae47-8355-44b4-9a49-4585e73b57c6 · outbound

This paper cites AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.558563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.558563Z digest=sha256:8bb8d156acd6a8773498091dfc44e9ed262b5b451719cae2301b72c267313a94

Observation 2cb77686-93b0-4ec3-b1d2-14c51dc339d3 · outbound

This paper cites The troubling emergence of hallucination in large language models-an extensive definition, quantification, and prescriptive remediations.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them The troubling emergence of hallucination in large language models-an extensive definition, quantification, and prescriptive remediations

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.636648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.636648Z digest=sha256:cc756a5004c50b3d963e93393177678c86f2deec7edb27579c60428c25b0bcdf

Observation f5be0020-51e2-497b-a482-fc862d97bc40 · outbound

This paper cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.748823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.748823Z digest=sha256:20406041098100648b5f2f3cc4d815e8e0bda87476166f72614d45d9c5b987ed

Observation a8bae754-042d-47ae-980a-b912da186434 · outbound

This paper cites Cognitive architec- tures for language agents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Cognitive architec- tures for language agents

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.818597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.818597Z digest=sha256:ec53b2cc4cd6efe05bdd091d122b6aef54908484c1b30e504d4c242bd2e369b2

Observation 0e012ae4-4a40-4cdb-b393-49b5d79feeeb · outbound

This paper cites A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.860943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.860943Z digest=sha256:1ee129a59e1b99618c39c9d59aa9664cb7c51a31003f60b8492959fde0d8dd2b

Observation 15ac6a5b-4793-4018-9382-52aee1ada4ae · outbound

This paper cites A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:38.977744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:38.977744Z digest=sha256:fc7774e765f564bf81b4b8d5bf9a571ecff41e666af2b752b7a76a6ef2020f6e

Observation 9977dc3b-ac8f-49e9-95d4-f7c55d2c056d · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Chain-of-thought prompting elicits reasoning in large language models

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.041541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.041541Z digest=sha256:aa74088af04c8c01077a44af24217a3bbae4c62efa5cd6187462ba6e496cfff4

Observation c0cfa8e2-120d-4566-a7af-ecf1e5b52c96 · outbound

This paper cites Adversarial attacks on multimodal agents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Adversarial attacks on multimodal agents

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.119427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.119427Z digest=sha256:7b08384a09b6dd711a446d31aebe2cd739989e323c7739bb13094225ab3499e6

Observation c7993a8c-b131-43db-a755-b015f5702369 · outbound

This paper cites OS-Copilot: Towards Generalist Computer Agents with Self-Improvement.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them OS-Copilot: Towards Generalist Computer Agents with Self-Improvement

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.188142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.188142Z digest=sha256:d9cca695b9d44fb6f8af32558ad0a301ab849fec391914e2c117d123f842bc66

Observation f2d90d96-f95a-4928-9e1b-6b0c5e422e12 · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.300588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.300588Z digest=sha256:aa6e6fd10da1c4d02be943489a97baad9e6e43abde4be04bd3a81f15bfac6a94

Observation 93533467-36d7-41de-9837-9439022d3a6a · outbound

This paper cites AdvAgent: Controllable Blackbox Red-teaming on Web Agents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them AdvAgent: Controllable Blackbox Red-teaming on Web Agents

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.378280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.378280Z digest=sha256:80ba1883de95a76df2b8f82e4d2ecb0dc24c0330ee237ba51c4d33217af5e552

Observation f8860e49-de91-4121-9d63-e937a52cdc82 · outbound

This paper cites TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.489224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.489224Z digest=sha256:1999d8250d0d5a649b513d8815fbd5f119e84b2ac0d626924b36dae684332022

Observation e02f4beb-6747-45b5-a515-3a32c537d92a · outbound

This paper cites RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.600377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.600377Z digest=sha256:ab6604dfadbdb0b16bc288b5b2c2114658bbd74711bc8c16c73484044f54a995

Observation ee0414e0-5e93-4809-a1ab-a40d317c0b87 · outbound

This paper cites Swe-agent: Agent-computer interfaces enable automated software engineering.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Swe-agent: Agent-computer interfaces enable automated software engineering

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.713147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.713147Z digest=sha256:08a5db880a46c4f4d517ae2509b06a4dee0e88e4105654dbda5b5c9783b7a68d

Observation 6e7144c5-89b1-46ed-9368-88a3f2cc0049 · outbound

This paper cites Webshop: Towards scalable real-world web interaction with grounded language agents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Webshop: Towards scalable real-world web interaction with grounded language agents

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.849262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.849262Z digest=sha256:8d9b57718a8462e828741210dd5ff1a1f6b8d2d55921292ac8561be738768f34

Observation 59e0a441-0be8-445c-b2ae-823f232c8820 · outbound

This paper cites τ-bench: A benchmark for tool-agent-user interaction in real-world domains, 2024.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them τ-bench: A benchmark for tool-agent-user interaction in real-world domains, 2024

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:39.952700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:39.952700Z digest=sha256:3b8361d6db4798b499af46d21f55ef15e6736f1621d2103e3b33cff00554f323

Observation 41dcae31-c07f-4880-99ce-e9b7ce9dbc63 · outbound

This paper cites React: Synergizing reasoning and acting in language models, 2023.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them React: Synergizing reasoning and acting in language models, 2023

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:40.036737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:40.036737Z digest=sha256:14daba6295da89d21f1c744e7240c9328232687bd1200af19fddf86adcb729d0

Observation 0dc1cd65-df81-4ce4-b016-3dc6fb980dba · outbound

This paper cites Survey on Evaluation of LLM-based Agents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Survey on Evaluation of LLM-based Agents

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:40.100049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:40.100049Z digest=sha256:e498315e1b5d6382f2930f538aca685f44a7b526b8a0ed57e7e81cdbc7a568fd

Observation 2fa0340b-5ae2-4a86-bb6e-c55395cc9725 · outbound

This paper cites Attacking Vision-Language Computer Agents via Pop-ups.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Attacking Vision-Language Computer Agents via Pop-ups

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:40.188635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:40.188635Z digest=sha256:737e71ed7d025e911cb68a28eafab8e3340bcc5f2631f3336300538ad80f42b2

Observation c2ce1916-70f2-452b-932c-91f0b994785f · outbound

This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:40.295209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:40.295209Z digest=sha256:e6245b321d4d4530d0f1b9c2e6766f524d8fc8c94d73335d936a7b47d6c51c66

Observation 2de7c469-1031-4370-b4bd-78bed9ffcea1 · outbound

This paper cites Agent-as-a-Judge: Evaluate Agents with Agents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Agent-as-a-Judge: Evaluate Agents with Agents

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:40.376737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:40.376737Z digest=sha256:e725a06535ad60066676e2dfa5469ebd574060358e2d65eebbcc3b7f4362086f

Observation e28f248d-f8e0-4e19-a3a7-8bde0d2dab8a · outbound

This paper cites theagentcompany.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them theagentcompany

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:40.485603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:40.485603Z digest=sha256:dc9d12861056ac5b41438130e02af050ff1f158343b4ebc903f86f63a89136aa

Observation 3fa5b52c-faf5-4f81-9d08-0bfb99a306e3 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:40.562029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:40.562029Z digest=sha256:ec32f0ceefe4778a82b5d9d28031f573aae6f5dce87ca46ad40e6069eca064d2

Observation 2ef81b64-3609-4f70-b809-343664f9ce31 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:40.671622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:40.671622Z digest=sha256:f03b6819fff6515fa0587310a38b3faebfe2f64356af841baa151c9a5ce23867

Observation 8bd0619f-85ee-420e-a391-4b0b26752240 · outbound

This paper cites How long is the meeting expected to run?.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them How long is the meeting expected to run?

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:40.756493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:40.756493Z digest=sha256:b562058a6457603fa0b47f80421e7e55262ff1bf75be8cff50c8ecd0074810d6

Observation e2a0ebef-3a3b-44d7-89a5-52af21c1118d · outbound

This paper cites theagentcompany.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them theagentcompany

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:40.891679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:40.891679Z digest=sha256:33a5909359164b90d4fc565795a5347122692e4069c8cd406bc8182c2d305f88

Observation c57fa9c3-c1c1-41f1-bb1d-01585b09471a · outbound

This paper cites theagentcompany.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them theagentcompany

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:41.061805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:41.061805Z digest=sha256:1fcaaa22c7946b4e1ab83d7f245e61bb7711764cf268104a44d4f7e5e7ab2bd5

Observation 78673061-2a5a-4f11-acc5-f315c83c0ae3 · outbound

This paper cites Output Requirements • Output the entire updated accessibility tree, reflecting the inserted reply node.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Output Requirements • Output the entire updated accessibility tree, reflecting the inserted reply node

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:41.212687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:41.212687Z digest=sha256:307a8341df1a7882436bd2d045d1beccc8caee0f96e5a501dae132bf193e7d95

Observation fd26bed2-6f1e-45e0-926a-1528abc78b11 · outbound

This paper cites Hi Chen, please exclude suspended or reviewed staff.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Hi Chen, please exclude suspended or reviewed staff

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:41.375443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:41.375443Z digest=sha256:6bd042d50fa6be788807c48fd1effc27ae55ae940eac148a2b52b833cddec18a

Observation 9dbdd061-54ae-49b6-bba2-607e85d8bb8e · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:41.535900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:41.535900Z digest=sha256:136c401ff1308ba51b32ef493260c609ee067cf489ce448d8caf462da0a17679

Observation e3857992-e96c-4e29-bdee-ce15005ddc31 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:41.631635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:41.631635Z digest=sha256:d499d000b88cfa4c0bfd057c34add6499f8bf806c0b8c8c4551788d51aa7a3ef

Observation 6bd5711f-ba1c-498f-9620-a476140fac76 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:41.768491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:41.768491Z digest=sha256:5970dd8288f062b37a1d6c50ab433054b10e7c2c931da41533547ea8274d9de3

Observation 0c8bec67-d5dd-45f7-9a75-b884b246571a · outbound

This paper cites user_question.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them user_question

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:41.903481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:41.903481Z digest=sha256:48076c6cf88fe27bd615ed55df8edf3fbc316ef4f91af5fd4f1cf939208250b7

Observation 7e2a1f27-e313-4478-bcb3-0ca2654731d2 · outbound

This paper cites Then, we used the o4-mini model to automatically identify steps involving user switches.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Then, we used the o4-mini model to automatically identify steps involving user switches

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.007735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.007735Z digest=sha256:c91be2d4b7c2d8ae7d71c11861805e364599cbc023e6cd2015bcb9a6a424a91c

Observation dc231b73-c6e3-475f-82e6-3beed0249094 · outbound

This paper cites Offline huang_jie.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Offline huang_jie

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.051931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.051931Z digest=sha256:8180f0553379da69a3142791858195707ac8357daaedfba525525a8907355a1d

Observation a83111ed-d43c-4d8e-b3f4-293e54f633b6 · outbound

This paper cites last_step_action.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them last_step_action

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.121831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.121831Z digest=sha256:d0c02702e94ae92d25ebf53ee0a8b747488956603e3a375a170573cfa2f05ac9

Observation ad18dd5f-27df-406c-b2ab-ddb0b26a8f62 · outbound

This paper cites Incidents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Incidents

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.207988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.207988Z digest=sha256:ad6bc2b27b7b5e65a058699de19e0eca40acf31c8fc863cd59ff597ed892e749

Observation dc436ef0-b016-45e0-9e7b-8462c3c24c67 · outbound

This paper cites Incidents.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Incidents

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.304680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.304680Z digest=sha256:30c9b832b6cbcbeccdea73c9aec1c539f336db6d7fcc6935c907a3d3a2bb7402

Observation 407c10dd-dd01-4667-806a-9ddda99852ac · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.427134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.427134Z digest=sha256:84babe9c5fded7f050395f7b1c006b0b96cd1c0d1e4c9f0b64f0b654b3ce79d0

Observation 46d213bc-0bdf-48e9-a3c5-ca3baa8d940c · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.525229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.525229Z digest=sha256:c91f6ff81542acddbe2aff75b56a9170d53c17afa5855bc28ccef3b5620b0eb8

Observation 8af79034-fc6f-4ecb-9f2e-db814e8eb07f · outbound

This paper cites Catalog Definitions > Maintain Items.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Catalog Definitions > Maintain Items

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.632870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.632870Z digest=sha256:3e9b32df46c7bbb64c74253c2424e0490eecfeff3b17890a339f21d45b0ebbef

Observation 16d73eab-8c91-4f30-814b-890928970dff · outbound

This paper cites catalog items.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them catalog items

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.760004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.760004Z digest=sha256:a2bef805db12cd79d19e3e9889040f570f7f62b1bdb7989e98449a4dd3501fdc

Observation b94c6c7a-fc1d-47b2-94a8-5cd3ee23aeb0 · outbound

This paper cites Service Catalog.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Service Catalog

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.858540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.858540Z digest=sha256:685cfc316542ae0cff6e50962a47e848cccff10669314141474ae5187c08de5d

Observation faa7f7c1-fa62-446f-a8f1-d4fa760801c6 · outbound

This paper cites Apple MacBook Pro 15.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Apple MacBook Pro 15

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:42.944460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:42.944460Z digest=sha256:e64b1e984085911ad2ebc31a8670e6ad624e8b08398580536fee8081ca0c33a0

Observation c0f83bdc-64ab-486a-adf4-aa97c77f24a5 · outbound

This paper cites • Score 1: Agent does not report infeasibility but shows exploratory behavior—e.g., scrolling, going back, or waiting—indicating uncertainty or an attempt to verify feasibility.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them • Score 1: Agent does not report infeasibility but shows exploratory behavior—e.g., scrolling, going back, or waiting—indicating uncertainty or an attempt to verify feasibility

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:43.008438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:43.008438Z digest=sha256:fc4b8e45ab9141bc65201320577a3ebb820be1a7a3dc3da17e8479eadd6e38e9

Observation 477715be-34c3-4302-b7e0-975839d4506c · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:43.131054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:43.131054Z digest=sha256:b8709a7bbde365feb217b43d7b098a4f4a32565679e33e0b2ee5e727ec38a2ab

Observation ed23c757-4f16-4f3a-beeb-efcae2d1797f · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:43.225353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:43.225353Z digest=sha256:3ed18b6b022a6dac2bece1d6582a0476901a9561f17bfd32bd520074bd9086b8

Observation b135d7cc-52c7-48ad-9dcc-a629d5c4aefa · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:43.310369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:43.310369Z digest=sha256:b195d234565e97fbeecee103988f7f8c1c38be31bfb8f086929bd91d57a5c18e

Observation 8e66ba6f-4a69-4979-aa0b-69a2785df15f · outbound

This paper cites task_goal.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them task_goal

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:43.402968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:43.402968Z digest=sha256:33e8d6d0e776e8882db428d574123856b585299bf3182ccdc0207bd7da9b490c

Observation 03b1759d-07e7-460c-8248-6ec32a78d1b9 · outbound

This paper cites cutoff_step.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them cutoff_step

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-06T13:06:43.494115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:06:43.494115Z digest=sha256:5bcbd02cff773626dafba86150faf347b74cf116d557af33e8312b3fae925dbb

Observation 91c0b533-b46c-4592-8d8e-e51ac226b199 · outbound

This paper cites We observed three primary behavior types, ranging from fully trusting misleading instructions to correctly validating them before taking action.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them We observed three primary behavior types, ranging from fully trusting misleading instructions to correctly validating them before taking action

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.411405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:43.554060Z digest=sha256:2eecf0e9c55ac9d413c4016df6151918960c7021f80361cdd18ead300b489340

Observation 7086f6d4-c781-4f4b-b186-7b1dfcf95a06 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 75

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:51.399000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:43.594457Z digest=sha256:170458bb7cb0a51dbaa60691393d73cf8dd76667411e449604be9a5dc172750d

Observation 4d883290-160e-468c-be1d-d2c433ab6663 · outbound

This paper cites Step 1: Case Selection We construct erroneous-step instances by analyzing SWE-agent execution traces produced using GPT-4o.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Step 1: Case Selection We construct erroneous-step instances by analyzing SWE-agent execution traces produced using GPT-4o

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.386525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:43.662037Z digest=sha256:1700a88ab6cbab390e41c5514ed597613f7bc27e61e7d01a348b0b3bdfc54bf4

Observation 0a4b73f8-47e5-41ce-88fe-8babeb73f61f · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 77

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:51.374064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:43.735093Z digest=sha256:8f4ed6387034cd31d5d6ebe375cefff2879b2bd572634e5cec1340cef6e7b1de

Observation 389b659c-9851-4cd4-a61f-0a81367a976e · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 78

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:51.361593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:43.788805Z digest=sha256:75dfe2645063ec9201e1f3a3cdba40e438865957040a7427f3c54881cd4ee567

Observation 15edc5fc-18b5-4f65-8350-6f46532a3e02 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 79

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:51.250186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:43.849351Z digest=sha256:9f04ecbd87e81dc068417ad5145caeb179b03ab6aac6bef1bca0c9cd4d896338

Observation 01ea2e38-f15a-47d4-8b6f-f8b943be0933 · outbound

This paper cites is_hallucination.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them is_hallucination

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.238139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:43.938961Z digest=sha256:a0093abc00fb398e1e3d2281e7d1199f7224b62654d49f7944462bb63008f0a3

Observation a88a6ce2-0c5c-4474-9c39-5d3cd75e6844 · outbound

This paper cites Processing expression: {expr}.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Processing expression: {expr}

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.225540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:43.997960Z digest=sha256:4fa439683017535fb0c3cfaddde6e08f81de4e8b147999cf1e9fd616d33e2772

Observation 4076762a-140a-4ec2-a965-2d9781a31ca2 · outbound

This paper cites checking logs.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them checking logs

Reference 82

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.212471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.068170Z digest=sha256:ec9498c56675e343898011ed4a9233ea56bc4b1f607bfe0a33700260020d0ef2

Observation ebdf1197-2569-4b29-a0ac-e013d6b485b3 · outbound

This paper cites We manually verify that these repetitions are not due to environmental malfunctions but are instead caused by the agent repeatedly issuing invalid actions.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them We manually verify that these repetitions are not due to environmental malfunctions but are instead caused by the agent repeatedly issuing invalid actions

Reference 83

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.199698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.147523Z digest=sha256:d374eee7c8f9e10f27440dc5a594012f5c682f2e5e477d9b9f714656473e79d0

Observation 976031b5-005e-464c-9126-ba2bb3d99598 · outbound

This paper cites Ideally, agents take alternative actions while explicitly acknowledging prior repetitions in their reasoning.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Ideally, agents take alternative actions while explicitly acknowledging prior repetitions in their reasoning

Reference 84

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.186286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.214027Z digest=sha256:f66bcf6f89b6a7f6bace1f372d2cb82a88fc8d79f3b71c7ce15e9c84e7e8422f

Observation 2f30a1ff-efe7-49f3-9f5d-2ade6eb4a619 · outbound

This paper cites action_history.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them action_history

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.174029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.307125Z digest=sha256:7e592bfe3d6162d742e9ca0448ce9a524191372895d005f223658580f4ea25ed

Observation 23bc170b-7ff5-40a2-a399-ecbd09403943 · outbound

This paper cites Therefore, we first collect pop-up examples observed in OSWorld and summarize their structure to create a reusable accessibility template.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Therefore, we first collect pop-up examples observed in OSWorld and summarize their structure to create a reusable accessibility template

Reference 86

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.161632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.397093Z digest=sha256:f652930b6f7155a6b99d6587b0636e699baf0d5f078cf4328002e0fea083d0ce

Observation 8e7507a0-302b-4d2b-9d48-4f8c7eab3f73 · outbound

This paper cites Preserve all elements of the template and maintain consistent formatting and structure.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Preserve all elements of the template and maintain consistent formatting and structure

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.148612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.495382Z digest=sha256:64d1b80f606717db1bc2bc5ba0e49e83f05fcd006f359ef8b55bd70d4a3e6662

Observation d931536e-dc67-4384-856b-47869c8f59b0 · outbound

This paper cites Invite collaborators to my repo,.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Invite collaborators to my repo,

Reference 88

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.136257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.576284Z digest=sha256:e12554e9805e4c5887977de694e0482e133700620d9ec27a7417f3d450b82a91

Observation 10ef4387-48aa-4e98-90e9-18cbf79b4d24 · outbound

This paper cites UPDATE NOW!.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them UPDATE NOW!

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.124213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.676575Z digest=sha256:2b1df8ae959ebeb5aa12fc6a94f842c23d9a3024a3152ca66dd250f62ca3fc25

Observation c4d7ca84-09bd-41be-9ee7-ae02eb687e2e · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 90

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:51.111116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.762130Z digest=sha256:8e3b758042e44ea4e8c69afb10f991302968bd3c869f5f5b9317e146c39070ad

Observation df9d99d3-48a8-4e6b-8a00-079a610a29c2 · outbound

This paper cites Output Format: • Output only the accessibility tree of the newly generated popup.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Output Format: • Output only the accessibility tree of the newly generated popup

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.098290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.827853Z digest=sha256:9ab85769cb6533cb409dfabe98944dea0730538b51452f27821c42c8deb3b2ad

Observation 8ccd9a0e-9566-416d-8eba-f1287ac6dc3f · outbound

This paper cites Preserve all structural elements and formatting.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Preserve all structural elements and formatting

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.084942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.893515Z digest=sha256:47db81d25bf8d5d23229934cb5ef14d6dc69a5c24e1b9ef3a439cb59fe1da8b2

Observation 08e31618-0481-4466-98c2-5009fdd393ce · outbound

This paper cites Example: If the goal is to buy a mattress, the first promotion must be for a mattress or related item.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Example: If the goal is to buy a mattress, the first promotion must be for a mattress or related item

Reference 93

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.072362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:44.965505Z digest=sha256:1714773646b6e3be42fe18e87aca94f015dedac2dc05b4d61971fc5ce87649b2

Observation f2d737c4-664e-4528-b36a-6c03a86ee6e6 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 94

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:51.059769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:45.030184Z digest=sha256:0601bd737c7ef607dae95a2d2ab32f950da2f893648a1bbfc05a5ded8ca3186a

Observation 68d22e43-ad24-4324-af76-1021c7d2bd1e · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 95

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:51.046665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:45.132634Z digest=sha256:369c53439f43d851393da5995ffdd4fd16b3d58722a60f55bab3b0cb2b7dfab5

Observation 28177ab9-d034-42ba-9723-b31be3e8ffb3 · outbound

This paper cites Do not include any explanatory comments or surrounding text.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Do not include any explanatory comments or surrounding text

Reference 96

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T13:06:51.033221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:45.233220Z digest=sha256:935af1c3ead4a363d819d2b949a2f5d819035aa9618436d314a0e3a297aefe52

Observation e245cc9e-116f-4d12-90c1-37b7403f7ae7 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 97

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:51.020733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:45.338167Z digest=sha256:4152baff4ebc9e144e66e94e4225ebb9c96538dca9eef85d1506dfa26bba6bd3

Observation d3852f18-72ce-49c9-996e-d62ff1133bd0 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 98

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:51.008485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:45.435342Z digest=sha256:52bd106e2e4332d982a224c6f8be15cf907f422adbb0fc0fd88c863c15c1393b

Observation 7ddd6caf-43b9-4c20-96a9-353f366a7175 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 99

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:50.995859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:45.507371Z digest=sha256:550044837f427bf89108ac5fbfaf81b1a5791dea03771765e46bc3818df6faf5

Observation b7e89c3b-39c0-427f-99de-16b9d8d74948 · outbound

This paper cites an unresolved cited work.

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them Unresolved cited work

Reference 100

Resolution
unresolved
raw_fallback, observed 2026-08-06T13:06:50.983089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T13:06:45.612718Z digest=sha256:b48aa0102d4c0e7a22007776c5ce1fa568573d8e444d919f940c9ed2993b2463

Pith citing papers

Observation 7f57ba85-e680-4762-bfee-c9e23240653f · inbound

CODE-GEN: A Human-in-the-Loop RAG-Based Agentic AI System for Multiple-Choice Question Generation cites this paper.

CODE-GEN: A Human-in-the-Loop RAG-Based Agentic AI System for Multiple-Choice Question Generation MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them

Reference 31

Resolution
unresolved
no resolver link, observed 2026-07-13T11:58:11.319217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-13T11:58:11.319217Z digest=sha256:d9fc2bb745f1f2ef6b66b9d161c5a3017295b440d604a1a1e575eb5361f1f6d7

Observation 1558e2c4-cf73-4e1f-b167-0c828bf8b038 · inbound

Program Analysis Guided LLM Agent for Proof-of-Concept Generation cites this paper.

Program Analysis Guided LLM Agent for Proof-of-Concept Generation MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them

Reference 44

Resolution
verified exact
arxiv_id, observed 2026-05-11T07:36:00.140158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-10T17:05:01.812948Z digest=sha256:82e38bfcb97c42318e1c2a077dc75258bcfb8e07ac7680561e756c1d1b4a179e

Observation 52d6c6ab-46f6-4233-ba9c-d886eff3fcdb · inbound

Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows cites this paper.

Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them

Reference 12

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T15:44:48.489125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-30T15:37:49.689481Z digest=sha256:1138508d1ddb767484027521a31267a42d38ae2b509590084482672dc5ecfff4

Observation 278b1612-001e-4336-b99f-c525c5dd1281 · inbound

Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities cites this paper.

Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-02T04:47:03.643606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:47:03.643606Z digest=sha256:91e1d9c1299f598b872af2511d0ab91a19292ab6aa28b9fb87f8d49bc66fdae4

Observation 19c94a0b-b8ac-43f9-ad43-76a342e2aa32 · inbound

Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities cites this paper.

Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-02T04:47:03.693039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:47:03.693039Z digest=sha256:b457d7f68b0bb0755d4dbd3ac199ecce03176fc3f2e080d703a0cf79f23bde92