Ctx2Skill: Self-Improving Framework for Autonomous Context-Skill Discovery in LLMs

Research official 2 src. ~1 min

The paper introduces Ctx2Skill, a self-improving framework for autonomous context-skill discovery in language models. A multi-agent self-play loop pits a Challenger (generating probing tasks) against a Reasoner (solving them using evolving skills), with a Judge providing feedback and a Cross-time Replay mechanism preventing skill degradation. Tested on four context-learning benchmarks, Ctx2Skill consistently improves performance across different LLM backbones without any human-authored skills.

Why it matters

128 upvotes on HuggingFace Daily Papers (May 5). Addresses a core bottleneck in agentic LLM systems: automatically extracting and reusing procedural knowledge from context rather than relying on hard-coded or human-curated skill libraries.

Importance: 3/5

128 HF Daily Papers upvotes; addresses core bottleneck in agentic self-improvement without human-curated skills.

agents reasoning rl self-improvement multi-agent paper

Sources

official From Context to Skills: Can Language Models Learn from Context Skillfully? — arXiv

official From Context to Skills on HuggingFace Daily Papers