arXiv AI July 1, 2026 By Zewen Liu

Calibrating the Evaluator: Does Probability Calibration Mitigate Preference Coupling in LLM Agent Feedback Loops?

arXiv:2606. 31371v1 Announce Type: cross Abstract: When large language model (LLM) agents adapt their behavior through evaluator feedback, systematic evaluator biases propagate into the agent's learned strategy distribution - a phenomenon termed evaluator preference coupling.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 29

Multimodal Evaluator Preference Collapse: Cross-Modal Coupling in Self-Evolving Agents

arXiv:2606. 16682v3 Announce Type: replace Abstract: When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases emerge.

By Zewen Liu

llms agents multimodal

arXiv Machine Learning

Jul 2

EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems

arXiv:2607. 00297v1 Announce Type: new Abstract: When LLM agents use evaluator feedback to adapt their behavior in closed loops, evaluator biases propagate through the agent's strategy distribution -- a phenomenon known as evaluator preference coupling.

By Zewen Liu

llms agents

arXiv AI

Aug 12

Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents

arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.

By Bhaskar Gurram

llms agents benchmarks

arXiv Machine Learning

Jun 30

A Diagnostic Framework and Multi-Evaluator Audit of Evaluator-Driven Preference Dynamics in Self-Adapting LLM Agents

arXiv:2606. 29719v1 Announce Type: new Abstract: Measurements of proprietary LLM evaluators can become invalid within weeks -- we document one case and provide the diagnostic framework to detect it.

By Liu Zewen

llms agents multimodal benchmarks

arXiv AI

Jun 3

Quantifying and Mitigating Self-Preference Bias of LLM Judges

arXiv:2604. 22891v4 Announce Type: replace-cross Abstract: LLM-as-a-Judge has become a dominant approach in automated evaluation systems, playing critical roles in model alignment, leaderboard construction, quality control, and so on.

By Jinming Yang, Zheng Hu, Chuxian Qiu, Zhenyu Deng, Xinshan Jiao, Tao Zhou

llms benchmarks safety

arXiv Machine Learning

Jun 16

Multimodal Evaluator Preference Collapse: Cross-Modal Contagion in Self-Evolving Agents

arXiv:2606. 16682v1 Announce Type: new Abstract: When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases emerge.

By Zewen Liu

llms agents multimodal

Related stories

Multimodal Evaluator Preference Collapse: Cross-Modal Coupling in Self-Evolving Agents

EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems

Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents

A Diagnostic Framework and Multi-Evaluator Audit of Evaluator-Driven Preference Dynamics in Self-Adapting LLM Agents

Quantifying and Mitigating Self-Preference Bias of LLM Judges

Multimodal Evaluator Preference Collapse: Cross-Modal Contagion in Self-Evolving Agents