# From Context to Skills: Can Language Models Learn from Context Skillfully?

arXiv: https://arxiv.org/abs/2604.27660 · HTML: https://mlsanity.com/paper/2604.27660/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 47 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 30 of 32)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills](https://mlsanity.com/paper/2504.07079/) (2025)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification](https://mlsanity.com/paper/2604.01687/) (2026)
- [AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution](https://mlsanity.com/paper/2603.01145/) (2026)
- [SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2506.24119/) (2025)
- [SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization](https://mlsanity.com/paper/2604.02268/) (2026)
- [SkillClaw: Let Skills Evolve Collectively with Agentic Evolver](https://mlsanity.com/paper/2604.08377/) (2026)
- [SkillX: Automatically Constructing Skill Knowledge Bases for Agents](https://mlsanity.com/paper/2604.04804/) (2026)
- [Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale](https://mlsanity.com/paper/2603.02176/) (2026)
- [SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents](https://mlsanity.com/paper/2305.13040/) (2023)
- [SkillNet: Create, Evaluate, and Connect AI Skills](https://mlsanity.com/paper/2603.04448/) (2026)
- [CL-bench: A Benchmark for Context Learning](https://mlsanity.com/paper/2602.03587/) (2026)
- [Search Self-play: Pushing the Frontier of Agent Capability without Supervision](https://mlsanity.com/paper/2510.18821/) (2025)
- [WebXSkill: Skill Learning for Autonomous Web Agents](https://mlsanity.com/paper/2604.13318/) (2026)
- [SkillOrchestra: Learning to Route Agents via Skill Transfer](https://mlsanity.com/paper/2602.19672/) (2026)
- [GATEAU: Selecting Influential Samples for Long Context Alignment](https://mlsanity.com/paper/2410.15633/) (2024)
- [A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks](https://mlsanity.com/paper/2510.05608/) (2025)
- [Context Engineering 2.0: The Context of Context Engineering](https://mlsanity.com/paper/2510.26493/) (2025)
- [Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering](https://mlsanity.com/paper/2502.07340/) (2025)
- [Survey of Self-Play in Reinforcement Learning](https://mlsanity.com/paper/2107.02850/) (2021)
- [Scaling Coding Agents via Atomic Skills](https://mlsanity.com/paper/2604.05013/) (2026)

## Built on by (most cited first, 19 of 19)

- [MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution](https://mlsanity.com/paper/2607.05297/) (2026)
- [SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution](https://mlsanity.com/paper/2605.18401/) (2026)
- [Step-wise Rubric Rewards for LLM Reasoning](https://mlsanity.com/paper/2605.17291/) (2026)
- [SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories](https://mlsanity.com/paper/2606.01311/) (2026)
- [Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.28424/) (2026)
- [Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs](https://mlsanity.com/paper/2605.30611/) (2026)
- [Agent Skill Evaluation and Evolution: Frameworks and Benchmarks](https://mlsanity.com/paper/2606.11435/) (2026)
- [Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems](https://mlsanity.com/paper/2606.18837/) (2026)
- [From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape](https://mlsanity.com/paper/2606.08625/) (2026)
- [Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement](https://mlsanity.com/paper/2605.26952/) (2026)
- [MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?](https://mlsanity.com/paper/2606.01993/) (2026)
- [Unsupervised Skill Discovery for Agentic Data Analysis](https://mlsanity.com/paper/2606.06416/) (2026)
- [SkillWiki: A Living Knowledge Infrastructure for Agent Skills](https://mlsanity.com/paper/2606.16523/) (2026)
- [Progressive Agent Skill Generation via Reinforcement Learning](https://mlsanity.com/paper/2608.01678/) (2026)
- [AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery](https://mlsanity.com/paper/2609.15820/) (2026)
- [Agents in the Large: Perception-Centered Architecture for Persistent Agents](https://mlsanity.com/paper/2608.30478/) (2026)
- [SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators?](https://mlsanity.com/paper/2608.30661/) (2026)
- [Self-Supervised Skill Optimization](https://mlsanity.com/paper/2607.28777/) (2026)
- [Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning](https://mlsanity.com/paper/2609.00759/) (2026)

## Abstract (arXiv)

Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive solution is inference-time skill augmentation: extracting the rules and procedures from context into natural-language skills. However, constructing such skills for context learning scenarios faces two challenges: the prohibitive cost of manual skill annotation for long, technically dense contexts, and the lack of external feedback for automated skill construction. In this paper, we propose Ctx2Skill, a self-evolving framework that autonomously discovers, refines, and selects context-specific skills without human supervision or external feedback. At its core, a multi-agent self-play loop has a Challenger that generates probing tasks and rubrics, a Reasoner that attempts to solve them guided by an evolving skill set, and a neutral Judge that provides binary feedback. Crucially, both the Challenger and the Reasoner evolve through accumulated skills: dedicated Proposer and Generator agents analyze failure cases and synthesize them into targeted skill updates for both sides, enabling automated skill discovery and refinement. To prevent adversarial collapse caused by increasingly extreme task generation and over-specialized skill accumulation, we further introduce a Cross-time Replay mechanism that identifies the skill set achieving the best balance across representative cases for the Reasoner side, ensuring robust and generalizable skill evolution. The resulting skills can be plugged into any language model to obtain better context learning capability. Evaluated on four context learning tasks from CL-bench, Ctx2Skill consistently improves solving rates across backbone models.