EASE: Behavior-Adaptive Skill Curation for Self-Evolving Agents

Agent skills provide a lightweight mechanism for self-evolving agents to accumulate reusable procedural knowledge without updating model parameters. However, existing learned skill curators typically optimize curation without explicitly modeling the behavior of the downstream executor. We show that this limitation can lead to systematic cross-executor degradation: curators optimized with different executors perform best when paired with their own training executor, suggesting that effective skill curation is executor-dependent. To address this challenge, we formulate behavior-adaptive skill curation and introduce $\text{EASE}$, a framework that learns a single curator capable of adapting its curation decisions to different executor behaviors. EASE maintains an online behavioral profile summarizing recent execution patterns and conditions the curator on this profile, together with the current trajectory and retrieved skills, to dynamically add, modify, or remove skills from an evolving repository. We train the shared curator jointly across multiple frozen executors with reinforcement learning, using retrieval-aware and behavior-aware temporal attribution to focus optimization on curation actions with observable downstream influence. Across multiple public agentic benchmarks, including ALFWorld, ScienceWorld, and WebShop, and heterogeneous executor families ranging from Qwen3-8B/32B and GPT-OSS-120B to previously unseen Kimi K2.6, DeepSeek V4 Flash, and Gemini 3.5 Flash, EASE outperforms strong skill- and memory-based baselines without per-executor finetuning. Beyond task performance, behavior-adaptive curation also enables more efficient skill evolution: across the three benchmarks, EASE maintains $34.5\sim 41.0$% fewer skills, improves skill retrieval by $36.3\sim 38.7$% and measured edit utility by $51.8\sim 60.0$%, and reduces deployment-time inference tokens by $9.1\sim 14.5$%. These results establish behavior-adaptive skill curation as an effective principle for building self-evolving agents. Anonymized code is available at https://anonymous.4open.science/r/EASE-skills.