# Agents of Change: Self-Evolving LLM Agents for Strategic Planning

arXiv: https://arxiv.org/abs/2506.04651 · HTML: https://mlsanity.com/paper/2506.04651/

## Key facts

- Cited by 21 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 25 of its 42 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 25 of 25)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization](https://mlsanity.com/paper/2310.16427/) (2023)
- [GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents](https://mlsanity.com/paper/2406.06613/) (2024)
- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)](https://mlsanity.com/paper/2302.06706/) (2023)
- [Lifelong Learning of Large Language Model based Agents: A Roadmap](https://mlsanity.com/paper/2501.07278/) (2025)
- [Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning](https://mlsanity.com/paper/2310.03249/) (2023)
- [CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents](https://mlsanity.com/paper/2401.10568/) (2024)
- [LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments](https://mlsanity.com/paper/2407.10031/) (2024)
- [Mastering Board Games by External and Internal Planning with Language Models](https://mlsanity.com/paper/2412.12119/) (2024)
- [Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example](https://mlsanity.com/paper/2408.06318/) (2024)
- [A Survey on LLM Inference-Time Self-Improvement](https://mlsanity.com/paper/2412.14352/) (2024)
- [On the Diagnostic of Road Pathway Visibility](https://mlsanity.com/paper/1601.05535/) (2016)
- [GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps](https://mlsanity.com/paper/2410.07765/) (2024)
- [Playing Catan with Cross-dimensional Neural Network](https://mlsanity.com/paper/2008.07079/) (2020)

## Built on by (most cited first, 21 of 21)

- [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)
- [LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions](https://mlsanity.com/paper/2509.18970/) (2025)
- [Self-Improvements in Modern Agentic Systems: A Survey](https://mlsanity.com/paper/2607.13104/) (2026)
- [Agent Exchange: Shaping the Future of AI Agent Economics](https://mlsanity.com/paper/2507.03904/) (2025)
- [Towards Agentic Self-Learning LLMs in Search Environment](https://mlsanity.com/paper/2510.14253/) (2025)
- [Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy](https://mlsanity.com/paper/2508.07485/) (2025)
- [The Era of Agentic Organization: Learning to Organize with Language Models](https://mlsanity.com/paper/2510.26658/) (2025)
- [Information Capacity: Evaluating the Efficiency of Large Language Models via Text Compression](https://mlsanity.com/paper/2511.08066/) (2025)
- [SAGE: Multi-Agent Self-Evolution for LLM Reasoning](https://mlsanity.com/paper/2603.15255/) (2026)
- [Self-Improvement of Large Language Models: A Technical Overview and Future Outlook](https://mlsanity.com/paper/2603.25681/) (2026)
- [Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?](https://mlsanity.com/paper/2512.06867/) (2025)
- [Galaxy: A Cognition-Centered Framework for Proactive, Privacy-Preserving, and Self-Evolving LLM Agents](https://mlsanity.com/paper/2508.03991/) (2025)
- [Shall We Play a Game? Language Models for Open-ended Wargames](https://mlsanity.com/paper/2509.17192/) (2025)
- [Towards AGI A Pragmatic Approach Towards Self Evolving Agent](https://mlsanity.com/paper/2601.11658/) (2026)
- [Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction](https://mlsanity.com/paper/2604.27221/) (2026)
- [Tools as Continuous Flow for Evolving Agentic Reasoning](https://mlsanity.com/paper/2605.07339/) (2026)
- [Self-evolving expertise in complex non-verifiable subject domains: dialogue as implicit meta-RL](https://mlsanity.com/paper/2510.15772/) (2025)
- [Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling](https://mlsanity.com/paper/2605.19418/) (2026)
- [SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems](https://mlsanity.com/paper/2606.03544/) (2026)
- [ViSculpt: Visual-Centric Agentic Geometry Editing](https://mlsanity.com/paper/2608.24169/) (2026)
- [Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?](https://mlsanity.com/paper/2610.08215/) (2026)

## Abstract (arXiv)

We address the long-horizon gap in large language model (LLM) agents by enabling them to sustain coherent strategies in adversarial, stochastic environments. Settlers of Catan provides a challenging benchmark: success depends on balancing short- and long-term goals amid randomness, trading, expansion, and blocking. Prompt-centric LLM agents (e.g., ReAct, Reflexion) must re-interpret large, evolving game states each turn, quickly saturating context windows and losing strategic consistency. We propose HexMachina, a continual learning multi-agent system that separates environment discovery (inducing an adapter layer without documentation) from strategy improvement (evolving a compiled player through code refinement and simulation). This design preserves executable artifacts, allowing the LLM to focus on high-level strategy rather than per-turn reasoning. In controlled Catanatron experiments, HexMachina learns from scratch and evolves players that outperform the strongest human-crafted baseline (AlphaBeta), achieving a 54% win rate and surpassing prompt-driven and no-discovery baselines. Ablations confirm that isolating pure strategy learning improves performance. Overall, artifact-centric continual learning transforms LLMs from brittle stepwise deciders into stable strategy designers, advancing long-horizon autonomy.