arXiv Machine Learning
When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Sep 28
SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting
SkillEvoReg is a regularization framework designed to mitigate overfitting in language-model agents that evolve reusable external skills. It combines training-time skill dropout, complexity-aware local regularization, and causal counterexample validation to control skill-state growth and detect regressions. Applied across SkillOpt, SkillEvolBench, and ContinualSkillBench, it preserves downstream performance while improving transfer and later-stage evolution outcomes.
arXiv Machine Learning
Oct 16
CausalEvo: Causal Skill Self-Evolution for Health LLM Agents
CausalEvo is a method that enables large language model agents in health to evolve their textual skills—such as calculation rules and measurement units—by evaluating the causal impact of skill changes while keeping model weights, feedback cases, and rule count constant. The approach freezes the LLM to propose candidate rules, pools them with existing skills, and uses paired skill replacements scored on shared feedback to rank and retain the most effective rules. In experiments on six MedCalc-Bench-Verified tasks, CausalEvo achieved 60.00% accuracy, outperforming SkillOpt (55.83%) and a no‑skill baseline (51.67%), while also reducing training token usage by 55.6%. whyItMatters":"CausalEvo demonstrates that controlled, causal evaluation of skill updates can improve health‑focused LLM performance and efficiency, directly benefiting the reliability and resource usage of medical language agents."
arXiv AI
Aug 5
Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds
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 AI
Jun 15
SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing
arXiv:2606. 14239v1 Announce Type: new Abstract: Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows.
arXiv Computation and Language
Aug 25
Can LLMs Truly Forget? Revealing Unlearning Gaps Through Adversarial Evaluation
arXiv:2608.21606v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating whet...
arXiv Computation and Language
Aug 25
When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents
The paper introduces Boundary-Aware Skill Memory (BASM), a method that enriches skill memories for large language model agents with explicit boundary fields such as applicability conditions, risk cues, avoidance rules, and recovery notes. This approach transforms retrieved skills from unconditional templates into state‑conditioned guidance, preventing the Skill Imitation Trap where more skills lead to incorrect tool usage. Experiments on three agent benchmarks and four model scales show that BASM improves task success rates, accuracy, and reduces attack success while cutting average steps compared to memory‑free baselines.