SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a challenging retrieval problem. Full-library prompting preserves coverage at high context cost, vector retrieval returns compact neighborhoods but treats skills as independent text, and graph-based retrieval can recover workflow context only when the edges that carry relevance are reliable. We propose CaSKG, a counterfactual-causal skill graph framework that calibrates procedural relations before retrieval. CaSKG first builds a high-recall directed

Read original source ↗ Open in workspace

recordType

paper

region

Global