# GEAR: Genetic AutoResearch for Agentic Code Evolution arXiv: https://arxiv.org/abs/2605.13874 ยท HTML: https://mlsanity.com/paper/2605.13874/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. - Builds on 32 of its 43 references that are in the map. - First posted on arXiv 8 May 2026. ## Placed in - LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/) ## Builds on (most cited first, 30 of 32) - [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) - [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024) - [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023) - [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023) - [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024) - [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015) - [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025) - [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025) - [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024) - [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025) - [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024) - [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025) - [EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers](https://mlsanity.com/paper/2309.08532/) (2023) - [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025) - [AI-Researcher: Autonomous Scientific Innovation](https://mlsanity.com/paper/2505.18705/) (2025) - [LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics](https://mlsanity.com/paper/2405.20132/) (2024) - [AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench](https://mlsanity.com/paper/2507.02554/) (2025) - [ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning](https://mlsanity.com/paper/2506.16499/) (2025) - [MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement](https://mlsanity.com/paper/2506.15692/) (2025) - [EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery](https://mlsanity.com/paper/2603.08127/) (2026) - [CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization](https://mlsanity.com/paper/2510.14150/) (2025) - [MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering](https://mlsanity.com/paper/2505.07782/) (2025) - [AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents](https://mlsanity.com/paper/2602.06855/) (2026) - [Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering](https://mlsanity.com/paper/2601.10402/) (2026) - [InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery](https://mlsanity.com/paper/2602.08990/) (2026) - [Toward Autonomous Long-Horizon Engineering for ML Research](https://mlsanity.com/paper/2604.13018/) (2026) - [Controlled Self-Evolution for Algorithmic Code Optimization](https://mlsanity.com/paper/2601.07348/) (2026) - [Monte Carlo Elites: Quality-Diversity Selection as a Multi-Armed Bandit Problem](https://mlsanity.com/paper/2104.08781/) (2021) ## Built on by (most cited first, 4 of 4) - [EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning](https://mlsanity.com/paper/2606.03108/) (2026) - [Personalized Auto-Research: Towards a True AI Co-Scientist](https://mlsanity.com/paper/2608.14881/) (2026) - [Loreley: Repository-Scale Program Evolution with Quality-Diversity Search](https://mlsanity.com/paper/2608.19703/) (2026) - [PrimeScientist: Strategic Allocation of Research Effort in Autonomous Research](https://mlsanity.com/paper/2609.17846/) (2026) ## Abstract (arXiv) Autonomous research agents can already run machine learning experiments without human supervision, but many rely on a narrow search strategy: they repeatedly modify one program and keep changes only when they improve the current best result. This can cause them to discard useful partial ideas, alternative promising directions, and insights from failed or incomplete experiments. GEAR, or Genetic AutoResearch, replaces this single-path search with a population-based search over multiple research states. It keeps a set of strong candidate solutions, selects parents based on productivity, novelty, and coverage, and explores new ideas through mutation and crossover. Each research state stores its code changes, reflections, and performance data, allowing future decisions to build on past discoveries. The paper studies three versions of GEAR: one controlled through prompting, one using a fixed programmatic search controller, and one where the controller itself can evolve during the run. Under the same compute budget and environment, all three versions outperform the AutoResearch baseline. More importantly, while the baseline tends to settle into one local optimum, GEAR continues finding improvements over longer runs. Overall, the results suggest that autonomous research agents become more effective when they maintain multiple promising directions and can adapt their search strategy over time.