arXiv cs.AIThursday · May 28, 2026FREE

SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment

llm-agentsreinforcement-learningskill-internalizationarxiv

SkillC, a new framework from arXiv cs.AI, addresses the challenge of skill internalization in LLM agents for long-horizon reinforcement learning. Unlike prior methods that only use skill-helpfulness contrast for curriculum control, SkillC directly converts this contrast into a learning signal via Contrastive Skill Credit Assignment (CSCA). It samples paired skill-injected and skill-free rollouts for tasks from active skill types within the same policy update, and injects their task-level contrast into optimization using a dual-stream advantage estimator. This estimator preserves global ranking while applying a one-sided correction toward skill-free success. A smoothed validation-level signal drives an adaptive curriculum over attribution strength, rollout allocation, and monotonic active-set pruning. Experiments on ALFWorld and WebShop demonstrate improved autonomous performance compared to baselines. The paper was published on May 28, 2026, under arXiv ID 2605.27899.

// why it matters

Enables LLM agents to autonomously perform tasks without external skill prompts, improving efficiency in long-horizon RL.

Sources

Primary · arXiv cs.AI
▸ Read original at arxiv.org

Like this? Get the next digest.