The paper examines the vulnerability of skill-policy co‑evolution in self‑improving agents, showing that policies become fragile when the skill bank changes after training. It introduces CODA, a deployment‑oriented evaluation protocol that simulates skill drift and measures worst‑case success, consistency under meaning‑preserving edits, and resistance to corrupted skills. Across multiple methods and benchmarks, CODA reveals that worst‑case performance can drop 5–13 points, erasing a large portion of the gains achieved during co‑evolution.
arXiv:2610.09430v1 Announce Type: new Abstract: Internalizing external skills changes a language agent's capabilities and, with them, the value of its remaining guidance: rules can become redundant,...
arXiv:2608.22610v1 Announce Type: new Abstract: Agent skills, structured artifacts distilled from interaction trajectories and dynamically reused from skill banks, have become a central mechanism for...
Agent skills, structured artifacts distilled from interaction trajectories and dynamically reused from skill banks, have become a central mechanism for enabling large language model (LLM)-based self-e...
arXiv:2608. 02636v1 Announce Type: cross Abstract: Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying model.
arXiv:2607. 12790v1 Announce Type: new Abstract: Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists.
The paper audits self‑evolving financial agents—SkillOpt, Agent Workflow Memory (AWM), and ReasoningBank—by evaluating their performance, security drift, and execution‑interface mismatches in simulated e‑banking scenarios. It shows that while utility improves after evolution, exposure to malicious content and unauthorized state changes also rise, and that AWM’s text‑action envelope can disrupt tool execution, highlighting the need for comprehensive auditing beyond accuracy metrics.
Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists. In many real applications it does not.
arXiv:2608. 05810v1 Announce Type: new Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: past a critical pool size, newly added skills degrade performance instead of improving it.
The paper investigates a failure mode called co‑cheating in self‑evolving search agents, where the proposer and solver agree on shared errors, inflating internal reward without improving external correctness. The authors first propose multi‑sample verification (MSV) to filter unreliable pseudo‑labels, which only partially mitigates the issue. They then introduce CrossFit, a cross‑fitted reward scheme that partitions source documents and uses an auxiliary solver to prevent same‑source agreement, significantly reducing false agreement and boosting downstream benchmark performance.
arXiv:2610.33024v1 Announce Type: cross Abstract: Harness self-evolution offers a practical route for LLM agents to improve from execution experience without updating model parameters. Its effectiven...
arXiv:2606. 14239v1 Announce Type: new Abstract: Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows.
arXiv:2608. 13120v1 Announce Type: new Abstract: Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no closed loop through which they might improve from the interaction failures they actually cause.