CDSE 方法让智能体技能按功能分化，36 项测试全面领先
From Trajectories to Differentiated Skills: Cognitive Differentiation for Self-Improving Agents
一篇讲怎么让智能体自己进化技能的论文，把技能拆成四个组件分别管理，36 个测试全拿了第一，搞 Agent 的可以看看。
论文提出 CDSE（Cognitive Differentiation in Skill Evolution），受认知科学启发，把单个智能体技能拆分为 Meta、Experience、Tool、Script 四个功能组件，并从成功与失败轨迹中提取语义梯度分别更新。作者对 500 个高排名技能包的分析显示 96.8% 包含至少两种功能角色的知识。在 6 个基准、3 个智能体模型、2 种执行框架共 36 个设置中，CDSE 全部取得最高分，比 Base 智能体提升 7.6 个百分点，比各设置中最强竞争方法平均高 2.6 分。
From Trajectories to Differentiated Skills: Cognitive Differentiation for Self-Improving Agents
Large language model (LLM) agents tackle complex tasks through reasoning and interaction with external environments. Agent skills provide persistent, transferable capabilities that guide task planning, inform contextual decisions, support tool use, and enable executable procedures. Yet existing skill-evolution methods largely organize knowledge around skill artifacts, overlooking the functional heterogeneity within individual skills and its implications for knowledge maintenance and use. Inspired by cognitive science, we propose Cognitive Differentiation in Skill Evolution (CDSE), which evolves a unified skill through four functionally distinct yet coordinated components: Meta, Experience, Tool, and Script. CDSE extracts evidence-grounded semantic gradients from successful and failed trajectories, consolidates them by functional role, and applies component-specific updates and validation with cross-component coordination and adaptive invocation. An analysis of 500 top-ranked skill packages shows that 96.8% contain knowledge spanning at least two functional roles. Across six benchmarks, three agent models, and two execution harnesses, CDSE achieves the highest scores in all 36 settings, improving over the Base agent by 7.6 percentage points and the strongest competing method in each setting by 2.6 points on average. Ablation studies further support the importance of functional differentiation and adaptive invocation.
