10 papers · 1 filter
UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
Xing Zhang, Guanghui Wang, Yanwei Cui +2
Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers' outputs, writes the final answer, allocates later call…
Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots
Xing Zhang, Yanwei Cui, Guanghui Wang +2
Agents improve quickly against a reliable automatic metric and stall without one, and the applications that need them most, report generation among them, are the ones nobody knows…
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…
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
Xing Zhang, Guanghui Wang, Yanwei Cui +4
Self-evolving agent systems create, revise, and retire their own skills, but every such loop assumes a reliable evaluation metric already exists. In many real applications none doe…
Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning
Yanwei Cui, Xing Zhang, Yulong Zhang +4
Training-free verbal reinforcement learning enables LLM agents to learn from world feedback -- objective signals such as dynamic task outcomes, market returns, or demand forecasts…
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…