Pith. sign in

Paper Citation Record · LEDGER

A Comprehensive Study of Implementation Bugs in Multi-modal Agents

As of 8 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:2607.04974.

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

pith.paper-citation-record.v1
2607.04974 v1

Coverage vector

measured 59 of 59 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T10:41:33.954036Z

measured 59 of 59 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

59 of 59 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved59
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8f0f7e36-4143-4acb-a312-b134b64a09b4 · outbound

This paper cites MARS: toward more efficient multi-agent collaboration for LLM reasoning,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents MARS: toward more efficient multi-agent collaboration for LLM reasoning,

Reference 1

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:8043acfd735eb88a458b29cd47a16fc0aa86f2d3e5f5a0e39e74bd61452aa769

Observation e3a3f973-2cdd-43a7-8c98-408ab8cbdce7 · outbound

This paper cites Agentic reasoning: A streamlined framework for enhancing LLM reasoning with agentic tools,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Agentic reasoning: A streamlined framework for enhancing LLM reasoning with agentic tools,

Reference 2

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:cfc07c2c107bab26e769704d0c1d99331c1ec43b49cf2689c4e903bce534506f

Observation f9670a87-8967-49b8-9959-47f6a599400c · outbound

This paper cites Agentless: Demystifying LLM-based Software Engineering Agents.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Agentless: Demystifying LLM-based Software Engineering Agents

Reference 3

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:335b8fb7d77af03d3e3a9bc71f25e5eff137740b45467d328be114315d63c04f

Observation 66712ed1-fce7-427d-b942-dcd4e8bc84eb · outbound

This paper cites Au- tocoderover: Autonomous program improvement,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Au- tocoderover: Autonomous program improvement,

Reference 4

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:8d83f889a41883031892b013b9d6d127e6325dcde6bb25f428a393e0641565ec

Observation b35d3def-a816-4c9f-9dbb-5dd4aa0adabe · outbound

This paper cites Openhands: An open platform for AI software developers as generalist agents,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Openhands: An open platform for AI software developers as generalist agents,

Reference 5

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:b133a5c01b034cf275c587d3623945d10673ab27117fd6e4d2b347021e87b3cf

Observation a2b5a9bc-c48b-4c68-9ece-16febb62b916 · outbound

This paper cites Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions

Reference 6

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:6cd726fe15ac85a286977838d7ef93c4894946169380defebc87944cd2fc9f4a

Observation 31fd7824-496d-4a0f-9e24-636907d9aede · outbound

This paper cites GPT-Driver: Learning to Drive with GPT.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents GPT-Driver: Learning to Drive with GPT

Reference 7

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:df32b3655a5841b31e2f34e47b1455aa45cad8912f6d07aecd774522a58f166c

Observation 506810c6-068d-4d4d-ac28-56ff195573b5 · outbound

This paper cites Drive like a human: Rethinking autonomous driving with large language models,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Drive like a human: Rethinking autonomous driving with large language models,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:fe7426dd0bdcd4958ecab235fcf45568ed382511757c54d9202b015bc746d132

Observation 7f97823f-4bd8-48f0-aaec-9b1c21057eed · outbound

This paper cites On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving

Reference 9

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:bcc60ca066a9c354bcdfe181ee296bb64b73251218c478dcabd8cee6e7173711

Observation 52155cf8-2c7c-4e20-a125-1cb2b1977808 · outbound

This paper cites MP5: A multi-modal open-ended embodied system in minecraft via active perception,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents MP5: A multi-modal open-ended embodied system in minecraft via active perception,

Reference 10

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:43f94403d54e878fa1fed30bc2e09e93fb69f14802d0ae335a2f2fadde4763a4

Observation 5405b8b9-5861-4451-9ab7-984d176c8a76 · outbound

This paper cites JAR VIS-1: open- world multi-task agents with memory-augmented multimodal language models,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents JAR VIS-1: open- world multi-task agents with memory-augmented multimodal language models,

Reference 11

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:7690485a59f28485c2b349aeff4599f6b7dd9ea640ce88b901b5586881cab67c

Observation 1335a719-6ab0-4712-8b26-e5690532dd0f · outbound

This paper cites Embodied multi-modal agent trained by an LLM from a parallel textworld,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Embodied multi-modal agent trained by an LLM from a parallel textworld,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:94d82ec163b52b58034a67e652ab911e84dc40fee8a82caccbbbde4731e50029

Observation 67fd4373-11be-46ef-aa67-fa188f970de0 · outbound

This paper cites Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents

Reference 13

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:93eb9929a8e5f22ca71300d5b9c1e680ef5c93901537ef3f79d347420fe8d8c1

Observation 12c60fe1-691c-444c-9c38-7c5c9c2b3e6f · outbound

This paper cites Webwise: Unlocking web interface control for llms via sequential exploration,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Webwise: Unlocking web interface control for llms via sequential exploration,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:b099d0d7b8da5b6e524e81ae76e5311d8af89590c1ec0261f6b55f1d55b8119c

Observation 62e69a25-5de6-4379-a507-7bac69b372f8 · outbound

This paper cites AutoDroid: LLM-powered Task Automation in Android.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents AutoDroid: LLM-powered Task Automation in Android

Reference 15

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:a2e684e27c8e1935c7e60e4e785f5c12162449a269ddd60a4d5052f917569a71

Observation 371fd33c-1012-40a5-9904-19bbd25c4142 · outbound

This paper cites GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:e3f3ebb8e9618a204f77b0518bce9c7619a716c078e564596f1f08cb3a8261be

Observation 9331f783-6026-475a-85e8-f4b4c52aea9c · outbound

This paper cites You only look at screens: Multimodal chain-of-action agents,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents You only look at screens: Multimodal chain-of-action agents,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:de72d5dd9218fdd222ffb36f11a127cae379e0933ed4a0df865eb064f9010e41

Observation bf6d669d-1fbd-48ec-9da3-8c41612349b6 · outbound

This paper cites Collision between vehicle controlled by developmental automated driving system and pedestrian,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Collision between vehicle controlled by developmental automated driving system and pedestrian,

Reference 18

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:35c8974d724bb82cbe7ea601f22e03df28a4089bf25375e0e13a85390c6279c7

Observation 24606737-970d-4939-93e7-deb25a7c63d5 · outbound

This paper cites Microsoft’s ai agent spends 100% of its testing funds on online fraud—lessons for msft and ai-secured transactions.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Microsoft’s ai agent spends 100% of its testing funds on online fraud—lessons for msft and ai-secured transactions

Reference 19

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:8987b48b8710781f9875bbdb53dcdb503f6919870c5463929d09a68bcd1bb00f

Observation 1c69e99b-e31b-434d-8bd6-c09b6f61d355 · outbound

This paper cites Chatgpt agent exposes vulnerability, potentially al- lowing “shadow leak.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Chatgpt agent exposes vulnerability, potentially al- lowing “shadow leak

Reference 20

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:beba795d1a0a1bddb58c0717513ebbd16ccdd470276f392f539ee2a6b129ab23

Observation 63595d95-1cf0-4faf-a3eb-c00e785de562 · outbound

This paper cites Security debt in llm agent applications: A measurement study of vulnerabilities andmitigation trade-offs,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Security debt in llm agent applications: A measurement study of vulnerabilities andmitigation trade-offs,

Reference 21

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:bd1d44dc8931dada4f935b54d4ec9c371d289ae7ab53bff207756016042beebb

Observation c52e18e5-89d6-4526-8a8e-2a058555a8da · outbound

This paper cites Eu- agent-bench: Measuring illegal behavior of LLM agents under EU law,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Eu- agent-bench: Measuring illegal behavior of LLM agents under EU law,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:5920618c9dd7ce5bf737710410c140fc575c88bb1d148cbe1f1ed4d74411e62e

Observation 044fb42a-54c3-4439-bd51-8977817b350c · outbound

This paper cites Can agents fix agent issues?.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Can agents fix agent issues?

Reference 23

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:9c9ba6fdfb5918bbdc13c27d0518674fcd92cf5bec8341b258dce0817db9e4ba

Observation a960a2a7-f90e-4b6b-b11f-bb6802eebbf8 · outbound

This paper cites Where LLM agents fail and how they can learn from failures,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Where LLM agents fail and how they can learn from failures,

Reference 24

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:06b7bad4f05de1fe89950dcf9159a616872c0a97cffa30c640fd7557c0999a19

Observation 4c98062c-cc03-4ee8-b1cf-f2cb4e182a60 · outbound

This paper cites Understanding software engineering agents: A study of thought-action-result trajectories,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Understanding software engineering agents: A study of thought-action-result trajectories,

Reference 25

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:e53026a23bb8c7e14ae55cbf75a2b66878bd7595eebc0f3b2455a1aef01e07f5

Observation 48cdf4ec-d62c-4dd6-be74-3d4a8525d164 · outbound

This paper cites Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study

Reference 26

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:ac21b1fe093f50053584b0fe937be0768858f0a902e54a6e3c5b8e1f7198dc36

Observation bdf7d7dd-97bd-4548-9add-ce33fcfe22eb · outbound

This paper cites Exploring autonomous agents: A closer look at why they fail when completing tasks,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Exploring autonomous agents: A closer look at why they fail when completing tasks,

Reference 27

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:dba014c20f5d7b6f4a521d33ec6cc8781e226d714c274594e3a51386e1977555

Observation 11b33f00-f64a-4468-921b-1f02e64faa29 · outbound

This paper cites SafeSearch: Automated Red-Teaming of LLM-Based Search Agents.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents SafeSearch: Automated Red-Teaming of LLM-Based Search Agents

Reference 28

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:adf86eafb8b9035a18aad27ecf8649e2aee549a9914bfa09379e8d3e614e9675

Observation a56b285e-e048-45c7-9830-be3c609ef3bd · outbound

This paper cites Why Do Multi-Agent LLM Systems Fail?.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Why Do Multi-Agent LLM Systems Fail?

Reference 29

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:76e68bd59765d2caa4b7f184c12ef209110da9cbfbca873e397abbf60e1c6bbe

Observation 50752fba-2576-49da-bfd3-52c6c730a3b0 · outbound

This paper cites Diagnosing failure root causes in platform-orchestrated agentic systems: Dataset, taxonomy, and benchmark,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Diagnosing failure root causes in platform-orchestrated agentic systems: Dataset, taxonomy, and benchmark,

Reference 30

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:685470e0c550f98c23283d2b1195c7d0a54f7d7f701b4877c1b9485f3479f47f

Observation 260ad4bc-e197-4cd7-86f6-40fdef60b238 · outbound

This paper cites Large Multimodal Agents: A Survey.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Large Multimodal Agents: A Survey

Reference 31

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:dcf7a124d6f63241659b7eb510ae679e07338175e105eec5e06388104661d2ab

Observation d42ca417-eb0e-405d-a573-bb70d2c78327 · outbound

This paper cites Large language model for verilog code generation: Literature review and the road ahead,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Large language model for verilog code generation: Literature review and the road ahead,

Reference 32

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:5c61b102f922c6c410892689b81bd23692d2c630ac89d2cb84ed0746ef6517fd

Observation 263a4b34-d26c-49a6-8a71-fd826b4c62ee · outbound

This paper cites Identifying relevant studies in software engineering,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Identifying relevant studies in software engineering,

Reference 33

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:d764ebfe8c78dde9f6d7071e21fccbd3c98b38d36c2c9132f491f2f42979686c

Observation 5254d7b8-b47e-49ec-8ddb-0f350eadfec6 · outbound

This paper cites Guidelines for snowballing in systematic literature studies and a replication in software engineering,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Guidelines for snowballing in systematic literature studies and a replication in software engineering,

Reference 34

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:07727189a693de1fd21484c42d202927bd9fd8763f65c6c9658229bec2daea56

Observation 1ffd2ac0-2a66-43ed-ab1d-42d79d2c8bac · outbound

This paper cites A comprehensive study of autonomous vehicle bugs,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents A comprehensive study of autonomous vehicle bugs,

Reference 35

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:004c16357963632b913218894f4e75a1a0b6782a88c1b0a40b094aa3fafcc24c

Observation f5769b8c-703f-4d2e-bb40-a07a0ab6daad · outbound

This paper cites Faults in deep reinforcement learning programs: a taxonomy and a detection approach,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Faults in deep reinforcement learning programs: a taxonomy and a detection approach,

Reference 36

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:47c8623ace5d02aa378c65421ab3d0511d3ff1bd8de35213c1b60808896b5541

Observation ff2ff986-9d13-4c51-8f10-0075bad99bb4 · outbound

This paper cites A comprehensive study of deep learning compiler bugs,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents A comprehensive study of deep learning compiler bugs,

Reference 37

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:9b097a4b0bd2dfd436093b7b520d058c7ec1b16fa7f2dbee571e9db0a894283c

Observation ce0376f0-5f4b-454a-8795-5a569f6d2d19 · outbound

This paper cites Catiss: An intelligent tool for categorizing issues re- ports using transformers,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Catiss: An intelligent tool for categorizing issues re- ports using transformers,

Reference 38

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:62778ffe8e7f78b33d3a3d38acad2afa60a423999abde1f78be315ac8a34ca3a

Observation 246ea148-9c06-4ed0-85bd-eece2e8590ce · outbound

This paper cites Analysis and detection of information types of open source software issue discussions,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Analysis and detection of information types of open source software issue discussions,

Reference 39

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:554bf6cc7e9c7a4207744819bbebecea4b2cc5d3582bb3b706115ea342c81ebf

Observation 076ab9e2-2bb4-4632-b967-38d3694e84e5 · outbound

This paper cites Bug characteristics in open source software,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Bug characteristics in open source software,

Reference 40

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:de091d117e8e188643fcf08c08a7de7b4e953072a3a512129606715bb2e5aec9

Observation 35868528-347e-4fea-9e07-82a1132f5a57 · outbound

This paper cites Cohen’s kappa coefficient as a performance measure for feature selection,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Cohen’s kappa coefficient as a performance measure for feature selection,

Reference 41

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:2ac37bd28feb315f06197549af3f974064fa227b5bc66bf21d12aa052a76a75b

Observation d09dab8a-1887-4426-94d6-6055c417098c · outbound

This paper cites CCFQA: A benchmark for cross-lingual and cross- modal speech and text factuality evaluation,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents CCFQA: A benchmark for cross-lingual and cross- modal speech and text factuality evaluation,

Reference 42

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:bd1e0c7ef653a2a7bc7e475b455378bb9a2fe63fbd4b5f9d3574dfc6ff0c80b6

Observation 6609a772-7c84-41f6-bd89-673a498deee9 · outbound

This paper cites Matester.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Matester

Reference 43

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:e2bdc7e616742613d56c0e8b5a5bc39e17a697da38eb9f7f816accdf0d5057ce

Observation cac71897-47e6-46f2-a389-fefc34f488ad · outbound

This paper cites Appagent: Multimodal agents as smartphone users,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Appagent: Multimodal agents as smartphone users,

Reference 44

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:85e235751897b8bee84cde64376576b3942e23a47b248f67e3c264b080700d6b

Observation 31d1f995-d905-4cbf-800b-3ede6564f241 · outbound

This paper cites DroidBot-GPT: GPT-powered UI Automation for Android.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents DroidBot-GPT: GPT-powered UI Automation for Android

Reference 45

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:d041db758f2f98021fcbf650c59ae53611497c381d348ad0581b2ccd83026f81

Observation f28a6a95-cc69-48b8-9aa0-3d3338680798 · outbound

This paper cites Mobilegpt: Augmenting LLM with human-like app memory for mobile task automation,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Mobilegpt: Augmenting LLM with human-like app memory for mobile task automation,

Reference 46

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:8bccf94783dce49090caee41241712fc42e8a492e7f3adbc0ba6dbe9011b3075

Observation 79c35e9d-a35e-423d-bc09-1b69f2c796ff · outbound

This paper cites ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation

Reference 47

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:7178755dbaf803ee8b7616c995932e08d5e308482326d29c5a6ff29a2a3171f6

Observation 5f66734e-2b27-495c-9cfe-fb6d953a10d1 · outbound

This paper cites Browsing like human: A multimodal web agent with experien- tial fast-and-slow thinking,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Browsing like human: A multimodal web agent with experien- tial fast-and-slow thinking,

Reference 48

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:bddc4f2580cdafd7a879230c5fbb68ca7f1386ce7acceb95e73f30947a814586

Observation ecf703b3-f86f-4838-9456-4f428aae7cdd · outbound

This paper cites Octopus: Embodied vision-language programmer from environmental feedback,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Octopus: Embodied vision-language programmer from environmental feedback,

Reference 49

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:ad14fe2dd603ee66023c025cc9fd58092dee93a37c484550f716cb3a25f48d3e

Observation 3e492c2d-bdfd-43d5-96ef-53f709d77063 · outbound

This paper cites See and think: Embodied agent in virtual environment,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents See and think: Embodied agent in virtual environment,

Reference 50

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:665a6f53445d56d227a1ec65fb19fc2802f513f0805d4a2dd427da1b6a23c558

Observation 8b49a3cc-2217-40e7-8226-e6e2e79ffc8c · outbound

This paper cites Open-world planning via lifted regression with llm-inferred affordances for embodied agents,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Open-world planning via lifted regression with llm-inferred affordances for embodied agents,

Reference 51

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:b936249667ae5fcd3d59dde5aebed106c483987b26e69f502443cdd4899c1b35

Observation 22576506-450a-448f-94dc-d2ae73cef06d · outbound

This paper cites Citynavagent: Aerial vision-and- language navigation with hierarchical semantic planning and global memory,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Citynavagent: Aerial vision-and- language navigation with hierarchical semantic planning and global memory,

Reference 52

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:d350b1029b5231d6e4a2a7a89d455af2fb4e9c63108905a672e66eeadc7a4b34

Observation 49d177c1-d310-4a85-a1c9-03cfcff5b6f4 · outbound

This paper cites RILA: reflective and imaginative language agent for zero-shot semantic audio-visual navigation,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents RILA: reflective and imaginative language agent for zero-shot semantic audio-visual navigation,

Reference 53

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:a8e594583f6a8c73585adf8f066cfbe3e588bad34504bb80d8d3c9686725fd68

Observation 9d9f1967-9619-4e5d-b923-c34257ae8a5a · outbound

This paper cites LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing

Reference 54

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:727c1190d3df7ca3f5c41c1b49dd389537a6d683150ef5c2a2d213b0ecde55df

Observation 746377dd-ed62-4931-93ce-2d2f922096ca · outbound

This paper cites Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

Reference 55

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:214d24b2754dec52fe00cb30843941cec4ed906405f8a17312ab0cb7a1a347ed

Observation 7af3603d-494f-4f1c-bd01-db6bec3a32f0 · outbound

This paper cites Genartist: Multimodal LLM as an agent for unified image generation and editing,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Genartist: Multimodal LLM as an agent for unified image generation and editing,

Reference 56

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:fcc6bbac559139a5dfc49aa5094056e86ec3c8b37c40951f8952384935daff39

Observation fd0920c3-ab5a-44c6-89b2-04731b33e30d · outbound

This paper cites Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative Editing.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative Editing

Reference 57

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:83acb68c4d75220a0aa4c568469f14568b700a8b82c6e60923912ccfc84b2b23

Observation 8e2f2a50-6a1d-47d8-8b6e-549dd9fdec0f · outbound

This paper cites Musicagent: An AI agent for music understanding and generation with large language models,.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents Musicagent: An AI agent for music understanding and generation with large language models,

Reference 58

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:c04144c5057e0220c9c20a1d84ffdc46e6b508272e31d00c14799cb4181300fa

Observation ca2d2db1-2031-469e-87e7-bc8d8cb18bea · outbound

This paper cites WavJourney: Compositional Audio Creation with Large Language Models.

A Comprehensive Study of Implementation Bugs in Multi-modal Agents WavJourney: Compositional Audio Creation with Large Language Models

Reference 59

Resolution
unresolved
no resolver link, observed 2026-07-11T10:41:33.954036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T10:41:33.954036Z digest=sha256:8eb766127fea53c18ca858b0e9a7b0ef2ce7c3b4aa57f28820714c59d78ba9b2

Pith citing papers

No inbound Pith citation observations are available.