# SkillWeaver：组合式技能路由用于LLM智能体

- 来源：elvis (@omarsar0)
- 发布时间：2026-06-18 22:42
- AIHOT 分数：40
- AIHOT 链接：https://aihot.virxact.com/items/cmqjmamb504qrslmhpsc3bpob
- 原文链接：https://x.com/omarsar0/status/2067618845926510770

## AI 摘要

传统LLM智能体技能路由仅从工具库选取单一技能，难以应对多技能组合的真实任务。本文形式化定义“组合式技能路由”，将复杂查询分解为原子子任务，为每个子任务检索对应技能并组合成可执行计划。系统SkillWeaver由LLM分解器、双编码器FAISS检索器和依赖感知DAG规划器构成。同时发布CompSkillBench基准，含300个组合查询和2,209个真实技能，直接评估多技能路由能力。DAG规划器将检索技能转化为有序、尊重依赖关系的计划。

## 正文

Cool paper on Skill routing for LLM agents.

Real tasks rarely map to a single skill. They need several composed together， but most skill routing still treats the problem as picking one tool from a library.

This work formalizes Compositional Skill Routing， decomposes a complex query into atomic sub-tasks， retrieves the right skill for each， and then composes an executable plan.

The system， SkillWeaver， pairs an LLM decomposer with a bi-encoder FAISS retriever and a dependency-aware DAG planner.

It comes with CompSkillBench， 300 compositional queries over 2，209 real skills， so the multi-skill case gets measured directly.

Why does it matter？

As skill libraries grow， single-skill retrieval quietly caps what an agent can do. The DAG planner turns retrieved skills into an ordered， dependency-respecting plan.

Paper： https://arxiv.org/abs/2606.18051

Learn to build effective AI agents in our academy： https://academy.dair.ai/