SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection

Paper recorded by Signals 4 on 2026-10-13 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-13 on arXiv · recorded by Signals 4 on 2026-10-14

Category: cs.LG · 机器学习 · first seen 2026-10-14

Abstract

Agentic reinforcement learning (RL) enables large language models (LLMs) to learn from multi-turn interactions with verifiable outcomes. Textual skills can improve exploration by distilling prior interactions into reusable guidance. However, existing skill-based RL approaches often either assume skill injection is beneficial or rely on indirect feedback or rollout-intensive evaluation to assess it

Read on arXiv →