arXiv Computation and Language By Zhiyuan Li, Linyuan Gao, Xuechun Ding, Hongwei Chen, Yuan Wu, Yi Chang

CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval

Read the original on arXiv Computation and Language →

CaSKG introduces a counterfactual‑causal skill graph framework that calibrates procedural relations before retrieval, building a high‑recall directed candidate graph from semantic, lexical, input/output, and structural evidence and refining it with repair evidence and optional LLM judgment. The framework applies direction‑conditioned textual counterfactual probes—removing, substituting, and reordering skill pairs—to aggregate evidence with Bayesian smoothing, producing a state‑filtered weighted graph for task‑conditioned expansion. Evaluated across six LLM backbones on ALFWorld and ScienceWorld, CaSKG outperforms existing Graph‑of‑Skills methods, improving macro‑average scores and reducing mean environment steps while preserving essential skill dependencies.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI
Jun 3

SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale

arXiv:2606. 03056v1 Announce Type: new Abstract: 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.

By Tong Bai, Zhenglin Wan, Pengfei Zhou, Xingrui Yu, Wangbo Zhao, Yang You, Ivor W. Tsang
Hugging Face Trending Papers
Aug 9

SkillReason: Reasoning-Enhanced Agent Skill Retrieval for Implicit User Requests

Large language model agents increasingly rely on reusable skills to extend their capabilities beyond parametric knowl- edge. However, retrieving the appropriate skill from a large- scale library remains challenging because realistic user re- quests are often concise and underspecified, stating only the task goal while leaving the required capabilities and execu- tion steps implicit.