SkillDAG：面向 LLM 大规模技能选择的自演化类型化技能图

View PDF HTML (experimental)

Abstract:Large skill libraries are now standard equipment for LLM agents, and which subset reaches the prompt decides what the agent can do. Enumeration and top-$K$ embedding retrieval both treat skills as independent documents, assuming relevance is a property of one skill at a time. It is not: skills depend on, conflict with, specialize, and duplicate one another, so the closest match to a task can name it while omitting a prerequisite it needs. Graph retrieval encodes these relations but spends them in a fixed pipeline, handing the agent an opaque bundle. We present SkillDAG, which exposes a typed skill graph to the LLM as an agent-callable interface rather than consuming it for the agent: search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets it register execution-backed edges as it works. Across two benchmarks and three model families, SkillDAG outperforms full-library prompting, vector retrieval, and Graph-of-Skills, gaining +14.3 points of ALFWorld success and tying only at ceiling; its ranking holds flat across a $10\times$ pool expansion that degrades the fixed pipeline. Inter-skill structure, these results suggest, is worth more to an agent that can query and revise it than to a retriever that consumes it.

Submission history

From: Tong Bai [view email]
[v1] Tue, 2 Jun 2026 02:45:21 UTC (4,274 KB)
[v2] Thu, 2 Jul 2026 14:01:29 UTC (4,448 KB)
[v3] Thu, 15 Oct 2026 03:28:10 UTC (3,636 KB)