SkillDAG：面向大规模LLM技能选择的自演化类型化技能图
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
AI总结：
提出SkillDAG，通过类型化有向图建模技能间关系，并作为推理时可调用的结构化检索接口，支持在线演化，在ALFWorld和SkillsBench上显著超越基线。
摘要：
随着LLM智能体采用大规模技能库，选择合适的子集成为一个结构性问题而非相似性匹配问题：技能之间存在依赖、冲突、特化或重复关系，这种结构对于全枚举和嵌入相似性都是不可见的。我们提出SkillDAG，将技能间关系建模为类型化有向图，并将其作为推理时、智能体可调用的结构化检索接口暴露给LLM智能体，在执行过程中查询和演化，而非固化在固定的检索流水线中：每次搜索返回向量匹配、类型化边邻居和冲突信号，并通过提议-提交协议让智能体注册基于执行的边，从而使图在多个回合中积累结构。在ALWWorld和SkillsBench上使用MiniMax-M2.7，SkillDAG达到67.1%的成功率和27.3%的奖励，比最强报告的Graph-of-Skills基线分别高出+12.8和+8.6个百分点；该优势可移植到gpt-5.2-codex，且在匹配查询下，内在SkillsBench Ret@K从65.5提升至78.2。这些增益可追溯到可隔离的机制：候选排序在池规模扩大10倍时保持鲁棒，而固定种子扩散流水线会退化；以及集合单调的在线编辑，在不驱逐先前命中项的情况下扩大地面真实召回率。
英文摘要：
As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend on, conflict with, specialize, or duplicate one another, a structure invisible to both full enumeration and embedding similarity. We present SkillDAG, which models inter-skill relationships as a typed directed graph and exposes it to an LLM agent as an inference-time, agent-callable structural retrieval interface, queried and evolved during execution rather than baked into a fixed retrieval pipeline: each search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets the agent register execution-backed edges so the graph accumulates structure across episodes. On ALFWorld and SkillsBench with MiniMax-M2.7, SkillDAG reaches 67.1% success and 27.3% reward, exceeding the strongest reported Graph-of-Skills baseline by +12.8 and +8.6 points; the advantage ports to gpt-5.2-codex, and intrinsic SkillsBench Ret@K rises from 65.5 to 78.2 under matched queries. These gains trace to isolable mechanisms: candidate ranking that stays robust as the pool grows 10x where a fixed seeding-diffusion pipeline degrades, and set-monotone online edits that enlarge ground-truth recall without evicting prior hits.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
