From the 1 of 10 linked papers with an AI index.
10 papers
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
Xing Zhang, Guanghui Wang, Yanwei Cui +4
The paper introduces a framework that co‑evolves evaluation metrics and the skills of LLM agents using an evolutionary loop guided by anchored reference sets, enabling transparent…
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
Xing Zhang, Yanwei Cui, Guanghui Wang +4
A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures? Skill retirement is the structural constraint that keeps…
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
Xing Zhang, Yanwei Cui, Guanghui Wang +4
Self-evolving skill libraries face a silent failure mode we term \emph{library drift}: unbounded skill accumulation without outcome-driven lifecycle management causes retrieval deg…
Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
Xing Zhang, Guanghui Wang, Yanwei Cui +4
As LLM agents scale to long-horizon, multi-session deployments, efficiently managing accumulated experience becomes a critical bottleneck. Agent memory systems and agent skill disc…
The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs
Xing Zhang, Guanghui Wang, Yanwei Cui +4
Telling an LLM to "be enthusiastic" raises its sycophancy rate from 30\% to 50\% on a lightly-aligned model, but has zero effect on a strongly-aligned one. We define this gap as th…
Guardrails Beat Guidance: A Large-Scale Study of Rules, Skills, and Persistent Configuration for Coding Agents
Xing Zhang, Guanghui Wang, Yanwei Cui +4
Random rules improve a coding agent's task performance as much as expert-curated ones (both pp on a discriminative subset of SWE-bench Verified), and in our data every indiv…