Paper Citation Record · LEDGER

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows

As of 9 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 2 inbound Pith citation observations for arXiv:2506.03332.

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

pith.paper-citation-record.v1
2506.03332 v1

Coverage vector

measured 70 of 70 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:10:45.767347Z

measured 72 of 72 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-22T03:53:03.807297Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T03:54:34.003611Z

Reference resolution

70 of 70 outbound references displayed

verified exact0
verified fuzzy21
unresolved47
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8b8395ea-c8c5-4af7-a3da-a1ff96abb61e · outbound

This paper cites ReConcile: Round-table conference improves reasoning via consensus among diverse LLMs.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows ReConcile: Round-table conference improves reasoning via consensus among diverse LLMs

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:48.042471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1361cfdc-fabe-4716-b7f6-8fefba645e89 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.521483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1676adec-811d-4096-b08f-16bcf22e89b1 · outbound

This paper cites Synthetic disinformation attacks on automated fact verification systems.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Synthetic disinformation attacks on automated fact verification systems

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:47.859384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b8f5c337-7361-4ea6-bcfd-9825eb220d40 · outbound

This paper cites Improving Factuality and Reasoning in Language Models through Multiagent Debate.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Improving Factuality and Reasoning in Language Models through Multiagent Debate

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.528343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aba0d3b-023e-48d5-8fb5-9a0f63d0116c · outbound

This paper cites DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.531959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9c8f781-43ed-4575-98e9-6d9d5f450882 · outbound

This paper cites SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.536054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c46706d3-b975-4a89-9062-bb9564179cb3 · outbound

This paper cites Baldur: Whole-Proof Generation and Repair with Large Language Models.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Baldur: Whole-Proof Generation and Repair with Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.540047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a53f184f-325a-4c2d-87ab-0386c753d6f8 · outbound

This paper cites CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.544006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 014c86a3-04a1-4df9-b5b7-e1cb9428fb57 · outbound

This paper cites The larger the better? improved LLM code-generation via budget reallocation.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows The larger the better? improved LLM code-generation via budget reallocation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:47.713786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 29a76a2f-4925-44d7-8582-e6a5c9d92acb · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Measuring Massive Multitask Language Understanding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.550880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 424f8645-1142-4952-b467-92cd4ba4e026 · outbound

This paper cites Large Language Models Cannot Self-Correct Reasoning Yet.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Large Language Models Cannot Self-Correct Reasoning Yet

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.554308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e438a02-8bcd-42db-ad95-d3711708e956 · outbound

This paper cites GPT-4o System Card.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows GPT-4o System Card

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.557635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 369e756e-bf62-4a64-828a-cc97e895e1f9 · outbound

This paper cites OpenAI o1 System Card.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows OpenAI o1 System Card

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.561129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d8abfcb-76f5-464c-ac2c-af43ba4c354c · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.564319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65cd85af-c690-480d-b6df-a537f449e9fd · outbound

This paper cites When can LLMs actually correct their own mistakes? a critical survey of self-correction of LLMs.Transactions of the Association for Computational Linguistics, 12:1417–1440, 2024.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows When can LLMs actually correct their own mistakes? a critical survey of self-correction of LLMs.Transactions of the Association for Computational Linguistics, 12:1417–1440, 2024

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:47.579967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 81f7c4be-d452-422d-9d8f-d5bd2c12d249 · outbound

This paper cites AI Agents That Matter.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows AI Agents That Matter

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.571170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec74cd6d-d6ba-485c-be06-83020276e60d · outbound

This paper cites Bowman, Tim Rocktäschel, and Ethan Perez.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Bowman, Tim Rocktäschel, and Ethan Perez

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:47.375433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 52cdb31c-8fde-43c1-9c84-baa153c6daca · outbound

This paper cites Natural questions: a benchmark for question answering research.Transactions of the Association for Computational Linguistics, 7:453–466, 2019.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Natural questions: a benchmark for question answering research.Transactions of the Association for Computational Linguistics, 7:453–466, 2019

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.577818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70b948cd-baec-4553-8abd-ef315209b3b4 · outbound

This paper cites Making language models better reasoners with step-aware verifier.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Making language models better reasoners with step-aware verifier

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.581968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e3d13e9-9249-4e03-8909-d85da7e37c06 · outbound

This paper cites Encouraging divergent thinking in large language models through multi- agent debate.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Encouraging divergent thinking in large language models through multi- agent debate

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:47.161684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b58eb157-5c5c-40ba-b168-9470b7f9814c · outbound

This paper cites Self-Refine: Iterative Refinement with Self-Feedback.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Self-Refine: Iterative Refinement with Self-Feedback

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.589027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6843d3e-326c-48dd-9049-be2657dc59ad · outbound

This paper cites Debate Helps Supervise Unreliable Experts.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Debate Helps Supervise Unreliable Experts

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.592227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b140cf55-d037-4299-a99d-98c319d50c95 · outbound

This paper cites Faitheval: Can your language model stay faithful to context, even if ”the moon is made of marshmallows”.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Faitheval: Can your language model stay faithful to context, even if ”the moon is made of marshmallows”

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.993915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0e540f63-cb26-4645-bd04-120ec0f23f93 · outbound

This paper cites Lever: Learning to verify language-to-code generation with execution.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Lever: Learning to verify language-to-code generation with execution

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.847888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a94a1d61-8e0d-470a-8a80-68e877edd8e6 · outbound

This paper cites On the Risk of Misinformation Pollution with Large Language Models.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows On the Risk of Misinformation Pollution with Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.601797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56114032-d189-4cae-8ef5-06c0cdd39060 · outbound

This paper cites OffsetBias: Leveraging Debiased Data for Tuning Evaluators.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows OffsetBias: Leveraging Debiased Data for Tuning Evaluators

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.605360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c3f49e0-dbb3-4f3a-828b-3ad7cfbcd84d · outbound

This paper cites Bowman, Amanda Askell, Roger Grosse, Danny Hernandez, Deep Ganguli, Evan Hubinger, Nicholas Schiefer, and Jared Kaplan.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Bowman, Amanda Askell, Roger Grosse, Danny Hernandez, Deep Ganguli, Evan Hubinger, Nicholas Schiefer, and Jared Kaplan

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.671505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a25700a9-0615-4de9-a465-29cc43230d9a · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Gpqa: A graduate-level google-proof q&a benchmark

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.611812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f78f1aca-f91e-42a5-b10a-e3c0dfaf3c88 · outbound

This paper cites Archon: An Architecture Search Framework for Inference-Time Techniques.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Archon: An Architecture Search Framework for Inference-Time Techniques

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.615625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78054db9-5947-4319-9573-31d6d4e47596 · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 64(9):99–106, 2021.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Winogrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 64(9):99–106, 2021

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.618993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41c39a13-2c28-46cd-89d4-ccd9cc75da88 · outbound

This paper cites Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.622334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31e67fda-94ee-45ba-bbfe-e651cdfd53fb · outbound

This paper cites an unresolved cited work.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:10:46.553778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 842dfd1d-5e0f-46ac-b200-c9efd47354d8 · outbound

This paper cites Practices for governing agentic ai systems.Research Paper, OpenAI, December, 2023.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Practices for governing agentic ai systems.Research Paper, OpenAI, December, 2023

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.535097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5e5cffbc-a1a3-4d63-a9b6-61944c43f564 · outbound

This paper cites Reflexion: Language Agents with Verbal Reinforcement Learning.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Reflexion: Language Agents with Verbal Reinforcement Learning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.632368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7aa50e3-d305-4872-9050-3b414728ed19 · outbound

This paper cites Inference scaling flaws: The limits of llm resampling with imperfect verifiers.arXiv preprint arXiv:2411.17501, 2024.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Inference scaling flaws: The limits of llm resampling with imperfect verifiers.arXiv preprint arXiv:2411.17501, 2024

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.636111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 659746c9-1a21-40c3-9810-e03b8f945461 · outbound

This paper cites Gemma 3 Technical Report.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Gemma 3 Technical Report

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.639268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b1b878d-ba31-4c7f-bde1-3703747c52e4 · outbound

This paper cites An in- context learning agent for formal theorem-proving.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows An in- context learning agent for formal theorem-proving

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.513148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2c8095f3-cbcc-4b22-9706-b030bf3a72e6 · outbound

This paper cites Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.650713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df1619c1-a459-40f1-b5a0-6510583c4d5c · outbound

This paper cites Toward self-improvement of llms via imagination, searching, and criticizing.Advances in Neural Information Processing Systems, 37:52723–52748, 2024.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Toward self-improvement of llms via imagination, searching, and criticizing.Advances in Neural Information Processing Systems, 37:52723–52748, 2024

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.654664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca280cb7-08fe-4757-b276-fb36c5ca5541 · outbound

This paper cites NewsQA: A Machine Comprehension Dataset.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows NewsQA: A Machine Comprehension Dataset

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.657768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02705d8d-9e81-4e3e-a8e6-e51996d1acca · outbound

This paper cites LEGO-prover: Neural theorem proving with growing libraries.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows LEGO-prover: Neural theorem proving with growing libraries

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.462307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 304c27ca-984c-4766-aaad-e5d1b58d3881 · outbound

This paper cites Resolving Knowledge Conflicts in Large Language Models.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Resolving Knowledge Conflicts in Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.665136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce2080a2-9371-4e44-8d81-267562a7ef10 · outbound

This paper cites Measuring short-form factuality in large language models.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Measuring short-form factuality in large language models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.669134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8160064c-d682-4a19-81db-c13f2bdcfb9e · outbound

This paper cites Simple synthetic data reduces sycophancy in large language models.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Simple synthetic data reduces sycophancy in large language models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.672950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 257dc43e-dd17-4bd5-a5ea-9a73874ed609 · outbound

This paper cites Examining inter-consistency of large language models collaboration: An in-depth analysis via debate.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Examining inter-consistency of large language models collaboration: An in-depth analysis via debate

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.422874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3503e66b-4cd2-435a-bd88-7619c505b8ca · outbound

This paper cites Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.679960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58d5fa96-f9fb-404b-884f-7bb3d5894e24 · outbound

This paper cites The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.684166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2452f366-8686-4d5c-acce-2afacc8d01fa · outbound

This paper cites Knowledge Conflicts for LLMs: A Survey.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Knowledge Conflicts for LLMs: A Survey

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.688349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03d51244-6295-4ae4-a1b1-348b5a65cd5e · outbound

This paper cites Qwen2.5 Technical Report.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Qwen2.5 Technical Report

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.691942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c4865fa-1973-4da3-a5e3-4519ccad2170 · outbound

This paper cites Generating Natural Language Proofs with Verifier-Guided Search.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Generating Natural Language Proofs with Verifier-Guided Search

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.695856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4df5328b-2433-4d1d-b33b-c9d76a162aa4 · outbound

This paper cites HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.699426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee76ef9b-3d3e-4419-8144-19406373b589 · outbound

This paper cites LLMCrit: Teaching large language models to use criteria.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows LLMCrit: Teaching large language models to use criteria

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.383357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 85143046-42f5-45bf-a161-4eab3dea9688 · outbound

This paper cites AFlow: Automating agentic workflow generation.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows AFlow: Automating agentic workflow generation

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.706946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83e44c2b-a4f8-483e-92bb-2e3918ca5c43 · outbound

This paper cites SituatedQA: Incorporating extra-linguistic contexts into QA.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows SituatedQA: Incorporating extra-linguistic contexts into QA

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T11:10:45.710982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7036bc86-9c64-44ad-9f76-3a3870d4ac62 · outbound

This paper cites Position- aware attention and supervised data improve slot filling.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Position- aware attention and supervised data improve slot filling

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.364770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9dc70918-abe1-4e64-99f7-dbe0d6ade062 · outbound

This paper cites Merging Generated and Retrieved Knowledge for Open-Domain QA.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Merging Generated and Retrieved Knowledge for Open-Domain QA

Reference 56

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T11:10:45.811721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fb463a37-ff55-4bdb-8faa-15fda3878e57 · outbound

This paper cites an unresolved cited work.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:10:46.355427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ee76e201-3308-4478-ad17-b3b5c3a75b4e · outbound

This paper cites an unresolved cited work.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:10:46.346548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 572d83ec-8ba1-4651-90bf-354c801e2a6b · outbound

This paper cites studies” or “statistics.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows studies” or “statistics

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.336953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 035fbc01-6134-4025-922f-234761dc69a8 · outbound

This paper cites an unresolved cited work.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:10:46.326832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4d7d511f-fe48-42b9-b46d-cb6b044086aa · outbound

This paper cites expert opinions.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows expert opinions

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.316400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 10b453a9-9b0f-49ce-820a-680c620ab5b3 · outbound

This paper cites an unresolved cited work.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:10:46.307058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 876b9632-643b-4d15-9a95-236dea98d87f · outbound

This paper cites an unresolved cited work.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:10:46.297727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation abeea410-1d77-4113-921e-e055787fb5c6 · outbound

This paper cites an unresolved cited work.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:10:46.287737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9e052475-cf78-4112-8276-42ded6e7cda6 · outbound

This paper cites Be creative and ruthless in your criticism.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Be creative and ruthless in your criticism

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.277779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a6288341-3502-4487-97de-6f57e5dd6779 · outbound

This paper cites Are you sure about this? I don’t think this answer is correct because.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Are you sure about this? I don’t think this answer is correct because

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.266954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a240727e-2006-44d5-9ecd-1242c28fe83e · outbound

This paper cites This conclusion seems hasty. What if.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows This conclusion seems hasty. What if

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.256950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bffffb8b-2a6b-4d8d-a43b-f864042d6cca · outbound

This paper cites I don’t think this follows logically because.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows I don’t think this follows logically because

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:10:46.245063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5eb77fa0-ba39-4b9c-a33d-d088f8b89736 · outbound

This paper cites an unresolved cited work.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Unresolved cited work

Reference 70

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T11:10:46.235130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8e63d4c5-bcba-478c-b046-9e21234a13b8 · outbound

This paper cites an unresolved cited work.

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:10:46.492842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation 7789b71c-de9e-4cfe-a038-da6c13ecd995 · inbound

The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents cites this paper.

The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:22:01.851015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 984043c9-0be9-42eb-b35b-bf409fdce334 · inbound

Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study cites this paper.

Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-22T03:54:34.006576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.