# Co-Evolving Skill Generation and Policy Optimization

arXiv: https://arxiv.org/abs/2606.08755 · HTML: https://mlsanity.com/paper/2606.08755/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 90 of its 96 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 30 of 90)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [ZeroSearch: Incentivize the Search Capability of LLMs without Searching](https://mlsanity.com/paper/2505.04588/) (2025)
- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills](https://mlsanity.com/paper/2504.07079/) (2025)
- [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026)
- [Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://mlsanity.com/paper/2504.07952/) (2025)

## Built on by (most cited first, 7 of 7)

- [UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation](https://mlsanity.com/paper/2606.29502/) (2026)
- [RLHarness: Co-evolving Procedural Skills with Reinforcement Learning for Long-horizon Multimodal Reasoning](https://mlsanity.com/paper/2609.32326/) (2026)
- [GenMem: Generative Symbolic Memory for Self-Evolving Harness](https://mlsanity.com/paper/2609.34633/) (2026)
- [SkillFM: Generating Skills for LLM Agents via Latent Flow Matching](https://mlsanity.com/paper/2609.39382/) (2026)
- [Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation](https://mlsanity.com/paper/2610.07250/) (2026)
- [Which Skill to Distill? SGUID: Selecting a Compact Skill Bank for Model-Skill Co-Evolution](https://mlsanity.com/paper/2610.12367/) (2026)
- [SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection](https://mlsanity.com/paper/2610.18807/) (2026)

## Abstract (arXiv)

Skill-augmented reinforcement learning improves language agents by storing reusable procedural knowledge acquired from past experience. Existing methods typically use strong language models to analyze trajectories, generate skills, and update a retrievable skill bank during online training. However, they rarely assess whether a newly generated skill is useful before it is stored and reused. We find that this assumption is unreliable: even skills generated by proprietary frontier LLMs exhibit highly mixed utility, with many providing little benefit or even degrading performance. Once such skills enter the bank, their effects are difficult to identify, because subsequent rollout feedback is delayed and usually reflects the combined effect of multiple retrieved skills rather than the marginal contribution of any individual skill. We propose an online reinforcement learning framework for pre-storage skill validation. The framework estimates whether a candidate skill contributes useful information beyond the skills already retrieved for the current task. It uses the standard rollout budget to form two matched groups under the same task and retrieval context: base rollouts conditioned on the currently retrieved skills, and skill-augmented rollouts conditioned on the same skills plus one candidate skill induced from the base trajectories. The reward gap between these two groups estimates the candidate skill's context-dependent marginal utility, enabling the framework to promote useful skills while filtering ineffective or harmful ones without additional rollout overhead. The framework further uses this marginal-utility signal to train the policy itself as a skill generator, reducing reliance on repeated calls to proprietary models. The learned skill-generation likelihood serves as a context-dependent score for retrieval-time reranking and outdated-skill pruning as the policy evolves.