EvoGuard: Mitigating Degradation in Online Skill Evolution
cs.CL
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Training-Free Group Relative Policy Optimization
- Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning
- SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models
- Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
- Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents
- Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
- Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills
- SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
- SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- AutoRefine: Compiling Trajectories into Validated Typed Agent Artifacts
- Progressive Agent Skill Generation via Reinforcement Learning
- Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
- From Context to Skills: Can Language Models Learn from Context Skillfully?
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data