# Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation

arXiv: https://arxiv.org/abs/2601.14691 · HTML: https://mlsanity.com/paper/2601.14691/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 36 of its 46 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 36)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [OS-Copilot: Towards Generalist Computer Agents with Self-Improvement](https://mlsanity.com/paper/2402.07456/) (2024)
- [Pixtral 12B](https://mlsanity.com/paper/2410.07073/) (2024)
- [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?](https://mlsanity.com/paper/2407.15711/) (2024)
- [Autonomous Evaluation and Refinement of Digital Agents](https://mlsanity.com/paper/2404.06474/) (2024)
- [Faithful Reasoning Using Large Language Models](https://mlsanity.com/paper/2208.14271/) (2022)
- [Process Reward Models That Think](https://mlsanity.com/paper/2504.16828/) (2025)
- [DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research](https://mlsanity.com/paper/2511.19399/) (2025)
- [AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories](https://mlsanity.com/paper/2504.08942/) (2025)
- [Stress Testing Deliberative Alignment for Anti-Scheming Training](https://mlsanity.com/paper/2509.15541/) (2025)
- [Scaling Test-Time Compute Without Verification or RL is Suboptimal](https://mlsanity.com/paper/2502.12118/) (2025)
- [Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models](https://mlsanity.com/paper/2506.13206/) (2025)
- [One Token to Fool LLM-as-a-Judge](https://mlsanity.com/paper/2507.08794/) (2025)

## Built on by (most cited first, 6 of 6)

- [AdaMEM: Test-Time Adaptive Memory for Language Agents](https://mlsanity.com/paper/2606.05684/) (2026)
- [Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models](https://mlsanity.com/paper/2602.03994/) (2026)
- [FraudSMSWalker: Benchmarking Agentic Large Language Models for SMS-to-Webpage Fraud Detection](https://mlsanity.com/paper/2606.16659/) (2026)
- [Testing and Evaluation of Agentic AI Systems In Military Command and Control](https://mlsanity.com/paper/2608.20597/) (2026)
- [SchemeArena: Factorized Stress Testing of Scheming in LLM Agents](https://mlsanity.com/paper/2609.08126/) (2026)
- [The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge](https://mlsanity.com/paper/2609.30604/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories including chain-of-thought (CoT) reasoning. This paradigm implicitly assumes that the agent's CoT faithfully reflects both its internal reasoning and the underlying environment state. We show this assumption is brittle: LLM judges are highly susceptible to manipulation of agent reasoning traces. By systematically rewriting agent CoTs while holding actions and observations fixed, we demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks. We study manipulation strategies spanning style-based approaches that alter only the presentation of reasoning and content-based approaches that fabricate signals of task progress, and find that content-based manipulations are consistently more effective. We evaluate prompting-based techniques and scaling judge-time compute, which reduce but do not fully eliminate susceptibility to manipulation. Our findings reveal a fundamental vulnerability in LLM-based evaluation and highlight the need for judging mechanisms that verify reasoning claims against observable evidence.