# Harnessing Agentic Evolution arXiv: https://arxiv.org/abs/2605.13821 ยท HTML: https://mlsanity.com/paper/2605.13821/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. - Builds on 32 of its 39 references that are in the map. - First posted on arXiv 13 May 2026. ## Placed in - LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/) ## Builds on (most cited first, 30 of 32) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023) - [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024) - [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024) - [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025) - [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023) - [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025) - [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024) - [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024) - [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016) - [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025) - [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026) - [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024) - [ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems](https://mlsanity.com/paper/2505.11831/) (2025) - [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025) - [Learning to Discover at Test Time](https://mlsanity.com/paper/2601.16175/) (2026) - [MemEvolve: Meta-Evolution of Agent Memory Systems](https://mlsanity.com/paper/2512.18746/) (2025) - [Evolved Policy Gradients](https://mlsanity.com/paper/1802.04821/) (2018) - [Hyperagents](https://mlsanity.com/paper/2603.19461/) (2026) - [Huxley-G"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine](https://mlsanity.com/paper/2510.21614/) (2025) - [CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery](https://mlsanity.com/paper/2604.01658/) (2026) - [Self-Supervised Prompt Optimization](https://mlsanity.com/paper/2502.06855/) (2025) - [AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration](https://mlsanity.com/paper/2602.03786/) (2026) - [Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search](https://mlsanity.com/paper/2502.17248/) (2025) - [DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework](https://mlsanity.com/paper/2510.17586/) (2025) - [AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines](https://mlsanity.com/paper/2602.14296/) (2026) - [Structured Scaling of AI Discovery Across Diverse Scientific Domains](https://mlsanity.com/paper/2604.19341/) (2026) - [RobustFlow: Towards Robust Agentic Workflow Generation](https://mlsanity.com/paper/2509.21834/) (2025) - [Learning to Continually Learn via Meta-learning Agentic Memory Designs](https://mlsanity.com/paper/2602.07755/) (2026) - [InteractComp: Evaluating Search Agents With Ambiguous Queries](https://mlsanity.com/paper/2510.24668/) (2025) ## Built on by (most cited first, 11 of 11) - [Rethinking the Evaluation of Harness Evolution for Agents](https://mlsanity.com/paper/2607.12227/) (2026) - [Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents](https://mlsanity.com/paper/2607.22688/) (2026) - [Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering](https://mlsanity.com/paper/2607.28568/) (2026) - [Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection](https://mlsanity.com/paper/2608.20169/) (2026) - [Scalable Environments Drive Generalizable Agents](https://mlsanity.com/paper/2605.18181/) (2026) - [ADIAS: Automated Design of Interactive Agentic Systems](https://mlsanity.com/paper/2608.06410/) (2026) - [VERSE: Verified Self-Evolving Optimizer for Agent Harnesses](https://mlsanity.com/paper/2610.02616/) (2026) - [Latent Action Reparameterization for Efficient Agent Inference](https://mlsanity.com/paper/2605.18597/) (2026) - [MemCodex: Self-Programming Hierarchical Memory for Language Agents](https://mlsanity.com/paper/2609.39765/) (2026) - [MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution](https://mlsanity.com/paper/2610.05300/) (2026) - [HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention](https://mlsanity.com/paper/2610.06563/) (2026) ## Abstract (arXiv) Agentic evolution has emerged as a powerful paradigm for improving programs, workflows, and scientific solutions by iteratively generating candidates, evaluating them, and using feedback to guide future search. However, existing methods are typically instantiated either as fixed hand-designed procedures that are modular but rigid, or as general-purpose agents that flexibly integrate feedback but can drift in long-horizon evolution. Both forms accumulate rich evidence over time, including candidates, feedback, traces, and failures, yet lack a stable interface for organizing this evidence and revising the mechanism that drives future evolution. We address this limitation by formulating agentic evolution as an interactive environment, where the accumulated evolution context serves as a process-level state. We introduce AEvo, a harnessed meta-editing framework in which a meta-agent observes this state and acts not by directly proposing the next candidate, but by editing the procedure or agent context that controls future evolution. This unified interface enables AEvo to steer both procedure-based and agent-based evolution, making accumulated evidence actionable for long-horizon search. Empirical evaluations on agentic and reasoning benchmarks show that AEvo outperforms five evolution baselines, achieving a 26 relative improvement over the strongest baseline. Across three open-ended optimization tasks, AEvo further outperforms four evolution baselines and achieves state-of-the-art performance under the same iteration budget.