# Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks

arXiv: https://arxiv.org/abs/2604.20987 · HTML: https://mlsanity.com/paper/2604.20987/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 46 of its 55 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 46)

- [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)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [R-Zero: Self-Evolving Reasoning LLM from Zero Data](https://mlsanity.com/paper/2508.05004/) (2025)
- [BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games](https://mlsanity.com/paper/2411.13543/) (2024)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [SoK: Agentic Skills -- Beyond Tool Use in LLM Agents](https://mlsanity.com/paper/2602.20867/) (2026)
- [MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory](https://mlsanity.com/paper/2601.03192/) (2026)
- [Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward](https://mlsanity.com/paper/2602.12430/) (2026)
- [A Survey on Large Language Model-Based Game Agents](https://mlsanity.com/paper/2404.02039/) (2024)
- [Reinforcement Learning for Self-Improving Agent with Skill Library](https://mlsanity.com/paper/2512.17102/) (2025)
- [Self-Rewarding Vision-Language Model via Reasoning Decomposition](https://mlsanity.com/paper/2508.19652/) (2025)
- [AgentEvolver: Towards Efficient Self-Evolving Agent System](https://mlsanity.com/paper/2511.10395/) (2025)
- [Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks](https://mlsanity.com/paper/2408.03615/) (2024)
- [XSkill: Continual Learning from Experience and Skills in Multimodal Agents](https://mlsanity.com/paper/2603.12056/) (2026)
- [Scaling Instructable Agents Across Many Simulated Worlds](https://mlsanity.com/paper/2404.10179/) (2024)
- [Language Instructed Reinforcement Learning for Human-AI Coordination](https://mlsanity.com/paper/2304.07297/) (2023)
- [lmgame-Bench: How Good are LLMs at Playing Games?](https://mlsanity.com/paper/2505.15146/) (2025)
- [Agentic Reinforcement Learning with Implicit Step Rewards](https://mlsanity.com/paper/2509.19199/) (2025)
- [VisPlay: Self-Evolving Vision-Language Models from Images](https://mlsanity.com/paper/2511.15661/) (2025)
- [Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play](https://mlsanity.com/paper/2509.25541/) (2025)

## Built on by (most cited first, 15 of 15)

- [Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading](https://mlsanity.com/paper/2607.08964/) (2026)
- [Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.10923/) (2026)
- [SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement](https://mlsanity.com/paper/2606.10546/) (2026)
- [SkillMaster: Toward Autonomous Skill Mastery in LLM Agents](https://mlsanity.com/paper/2605.08693/) (2026)
- [CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents](https://mlsanity.com/paper/2606.02372/) (2026)
- [COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows](https://mlsanity.com/paper/2607.01709/) (2026)
- [Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries](https://mlsanity.com/paper/2607.10113/) (2026)
- [Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems](https://mlsanity.com/paper/2606.18837/) (2026)
- [Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents](https://mlsanity.com/paper/2606.20631/) (2026)
- [The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.06663/) (2026)
- [Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security](https://mlsanity.com/paper/2608.29596/) (2026)
- [SkillCome: Group Contrast Skill Optimization with Dual Memory](https://mlsanity.com/paper/2609.37128/) (2026)
- [Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning](https://mlsanity.com/paper/2609.39473/) (2026)
- [VERA: Scaling Verifiable Environments for Agentic co-Evolution](https://mlsanity.com/paper/2610.05923/) (2026)
- [Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents](https://mlsanity.com/paper/2610.18082/) (2026)

## Abstract (arXiv)

Long horizon interactive environments are a testbed for evaluating agents skill usage abilities. These environments demand multi step reasoning, the chaining of multiple skills over many timesteps, and robust decision making under delayed rewards and partial observability. Games are a good testbed for evaluating agent skill usage in environments. Large Language Models (LLMs) offer a promising alternative as game playing agents, but they often struggle with consistent long horizon decision making because they lack a mechanism to discover, retain, and reuse structured skills across episodes. We present COSPLAY, a co evolution framework in which an LLM decision agent retrieves skills from a learnable skill bank to guide action taking, while an agent managed skill pipeline discovers reusable skills from the agents unlabeled rollouts to form a skill bank. Our framework improves both the decision agent to learn better skill retrieval and action generation, while the skill bank agent continually extracts, refines, and updates skills together with their contracts. Experiments across six game environments show that COSPLAY with an 8B base model achieves over 25.1 percent average reward improvement against four frontier LLM baselines on single player game benchmarks while remaining competitive on multi player social reasoning games.