# Dynamic Dual-Granularity Skill Bank for Agentic RL

arXiv: https://arxiv.org/abs/2603.28716 · HTML: https://mlsanity.com/paper/2603.28716/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 45 of its 49 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)

## Builds on (most cited first, 30 of 45)

- [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)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [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)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [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)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [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)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [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)
- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://mlsanity.com/paper/2504.07952/) (2025)
- [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026)
- [Language as an Abstraction for Hierarchical Deep Reinforcement Learning](https://mlsanity.com/paper/1906.07343/) (2019)
- [EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle](https://mlsanity.com/paper/2510.16079/) (2025)
- [MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory](https://mlsanity.com/paper/2601.03192/) (2026)
- [Memento: Fine-tuning LLM Agents without Fine-tuning LLMs](https://mlsanity.com/paper/2508.16153/) (2025)
- [G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems](https://mlsanity.com/paper/2506.07398/) (2025)
- [OpenClaw-RL: Train Any Agent Simply by Talking](https://mlsanity.com/paper/2603.10165/) (2026)
- [StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization](https://mlsanity.com/paper/2505.15107/) (2025)
- [AgentEvolver: Towards Efficient Self-Evolving Agent System](https://mlsanity.com/paper/2511.10395/) (2025)
- [Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers](https://mlsanity.com/paper/2603.07670/) (2026)

## Built on by (most cited first, 30 of 34)

- [SkillOS: Learning Skill Curation for Self-Evolving Agents](https://mlsanity.com/paper/2605.06614/) (2026)
- [CODESKILL: Learning Self-Evolving Skills for Coding Agents](https://mlsanity.com/paper/2605.25430/) (2026)
- [UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation](https://mlsanity.com/paper/2606.29502/) (2026)
- [Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents](https://mlsanity.com/paper/2605.10663/) (2026)
- [SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment](https://mlsanity.com/paper/2605.27899/) (2026)
- [Agent Skill Evaluation and Evolution: Frameworks and Benchmarks](https://mlsanity.com/paper/2606.11435/) (2026)
- [π-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data](https://mlsanity.com/paper/2604.14054/) (2026)
- [Co-Evolving Skill Generation and Policy Optimization](https://mlsanity.com/paper/2606.08755/) (2026)
- [SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems](https://mlsanity.com/paper/2606.01314/) (2026)
- [SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training](https://mlsanity.com/paper/2606.02355/) (2026)
- [Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems](https://mlsanity.com/paper/2606.18837/) (2026)
- [daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization](https://mlsanity.com/paper/2606.16497/) (2026)
- [MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deduction](https://mlsanity.com/paper/2605.08670/) (2026)
- [Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution](https://mlsanity.com/paper/2605.08887/) (2026)
- [STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery](https://mlsanity.com/paper/2605.17790/) (2026)
- [Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning](https://mlsanity.com/paper/2606.00510/) (2026)
- [MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents](https://mlsanity.com/paper/2607.24097/) (2026)
- [Coalition-Aware Skill Reliability for Self-Evolving Agents](https://mlsanity.com/paper/2608.22610/) (2026)
- [Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents](https://mlsanity.com/paper/2609.17653/) (2026)
- [HiSkill: Empowering LLM Agents with Hierarchical Skill Graphs](https://mlsanity.com/paper/2607.25853/) (2026)
- [Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner](https://mlsanity.com/paper/2608.23268/) (2026)
- [COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization](https://mlsanity.com/paper/2609.11682/) (2026)
- [You Live More Than Once: Towards Hierarchical Skill Meta-Evolving](https://mlsanity.com/paper/2605.28390/) (2026)
- [Beyond Rubrics: Exploration-Guided Evaluation Skills for Reward Modeling](https://mlsanity.com/paper/2606.07040/) (2026)
- [SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants](https://mlsanity.com/paper/2606.12984/) (2026)
- [SkillMentor: LLM Agent Self-Evolution via Learning Blind-Spot Diagnosis](https://mlsanity.com/paper/2607.27360/) (2026)
- [Search2Skill: Skill Distillation Beyond Knowledge Boundaries Via Rubric-Based Reinforcement Learning](https://mlsanity.com/paper/2608.05245/) (2026)
- [Competence, Not Accuracy: A Diagnostic for Reference-Free Judge Gates in Skill Optimization](https://mlsanity.com/paper/2608.18719/) (2026)
- [Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security](https://mlsanity.com/paper/2608.29596/) (2026)
- [CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution](https://mlsanity.com/paper/2609.04865/) (2026)

## Abstract (arXiv)

Agentic RL can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for maintaining an evolving skill memory. We propose D2Skill, a dynamic dual-granularity skill bank for agentic RL that organizes reusable experience into task skills for high-level guidance and step skills for fine-grained decision support and error correction. D2Skill jointly trains the policy and skill bank through paired baseline and skill-injected rollouts under the same policy, using their performance gap to derive hindsight utility signals for both skill updating and policy optimization. Built entirely from training-time experience, the skill bank is continuously expanded through reflection and maintained with utility-aware retrieval and pruning. Experiments on ALFWorld, WebShop, and Search-Augmented QA tasks show that D2Skill substantially improves performance over skill-free baselines across models of different scales. Further ablations and analyses show that both dual-granularity skill modeling and dynamic skill maintenance are critical to these gains, while the learned skills exhibit higher utility, transfer across evaluation settings, and introduce only modest training overhead.