GEAR: Genetic AutoResearch for Agentic Code Evolution

• URL: http://arxiv.org/abs/2605.13874v1
• Date: Fri, 08 May 2026 00:25:09 GMT
• Title: GEAR: Genetic AutoResearch for Agentic Code Evolution
• Abstract summary: GEAR, or Genetic AutoResearch, replaces a single-path search with a population-based search over multiple research states.<n>It keeps a set of strong candidate solutions, selects parents based on productivity, novelty, and coverage, and explores new ideas through mutation and crossover.<n>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.
• Score: 11.641689406945202
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• AutoResearch: Insight In, Hallucination Out [18.44583561825209]
  We introduce AutoResearch, a two-stage system that connects Idea Generation and Idea Execution.<n>In Idea Generation, AutoResearch continuously integrates emerging research signals with accumulated domain knowledge.<n>In Idea Execution, coordinated agents decompose these plans into experiments, iteratively implement and diagnose them, and employ independent evidence-based review.
  arXiv  Detail & Related papers  (2026-08-18T15:38:26Z)
• AutoScientist-Quant: Self-Evolving Coding Agents for Automatic Research in Quantitative Investment [28.36446889018906]
  We present AutoScientist-Quant, a self evolving search process that regards quantitative research as one budgeted search problem.<n>A single controller conditions every decision on the remaining budget, choosing at each round whether to improve, combine, pivot, or stop, which node to expand, how many alphas to generate, and how to retrieve past trajectories from the shared memory.<n>The framework attains the best value of nearly every metric in every setting, and these conclusions hold across several backbones and markets.
  arXiv  Detail & Related papers  (2026-08-05T23:34:46Z)
• Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty [39.97857268041792]
  Heuresis is a framework that abstracts the research pipeline into a set of general and composable primitives.<n>We find that completely novel ideas are rare. No idea across our scored runs is rated as "Original", and only a few achieve only "Minor Similarity" to prior work.
  arXiv  Detail & Related papers  (2026-06-23T21:44:08Z)
• Self-Improving Language Models with Bidirectional Evolutionary Search [93.21736992722835]
  Bidirectional Evolutionary Search (BES) is a search framework that couples forward candidate evolution with backward goal decomposition.<n>We provide theoretical motivation showing that candidates generated by expansion-only search are confined to a narrow entropy shell while evolutionary operators can escape it.<n> Experiments show that on challenging post-training tasks where mainstream post-training algorithms fail to improve, BES enables consistent gains.
  arXiv  Detail & Related papers  (2026-05-27T17:59:15Z)
• AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration [175.74514061083195]
  We present AutoResearchClaw, a multi-agent autonomous research pipeline built on five mechanisms.<n>On ARC-Bench, a 25-topic experiment-stage benchmark, AutoResearchClaw outperforms AI Scientist v2 by 54.7%.
  arXiv  Detail & Related papers  (2026-05-19T15:49:51Z)
• NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation [59.00873435874659]
  LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automation for whom?<n>We propose NanoResearch, a multi-agent framework that addresses these gaps through tri-level co-evolution.<n>A skill bank distills recurring operations into compact procedural rules reusable across projects.<n>A memory module maintains user- and project-specific experience that grounds planning decisions in each user's research history.<n>A label-free policy learning converts free-form feedback into persistent parameter updates of the planner, reshaping subsequent coordination.
  arXiv  Detail & Related papers  (2026-05-11T16:33:47Z)
• CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery [67.47220507982522]
  Large language model (LLM)-based evolution is a promising approach for openended discovery.<n>We present CORAL, the first framework for autonomous multi-agent evolution on open-ended problems.<n>CORAL replaces rigid control with long-running agents that explore, reflect, and collaborate.
  arXiv  Detail & Related papers  (2026-04-02T05:59:06Z)
• EvoX: Meta-Evolution for Automated Discovery [115.89434419482797]
  EvoX is an adaptive evolution method that optimize its own evolution process.<n>It continuously updates how prior solutions are selected and varied based on progress.<n>It outperforms existing AI-driven evolutionary methods including AlphaEvolve, OpenEvolve, GEPA, and ShinkaEvolve on the majority of tasks.
  arXiv  Detail & Related papers  (2026-02-26T18:54:41Z)
• OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery [10.217363774023033]
  OR-Agent is a multi-agent research framework designed for automated exploration in rich experimental environments.<n>We introduce an evolutionary-systematic mechanism that unifies evolutionary selection of research starting points, comprehensive research plan generation, and coordinated exploration within a research tree.<n>We conduct experiments across classical optimization benchmarks-including traveling salesman, capacitated vehicle routing, bin packing, orienteering, and multiple knapsack problems-as well as a simulation-based cooperative driving scenarios.
  arXiv  Detail & Related papers  (2026-02-14T13:32:03Z)
• From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking [48.90371827091671]
  AutoExperiment is a benchmark that evaluates AI agents' ability to implement and run machine learning experiments.<n>We evaluate state-of-the-art agents and find that performance degrades rapidly as $n$ increases.<n>Our findings highlight critical challenges in long-horizon code generation, context retrieval, and autonomous experiment execution.
  arXiv  Detail & Related papers  (2025-06-24T15:39:20Z)
• WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms [52.942566473658054]
  We enhance web agents with an explicit rollback mechanism, enabling the agent to revert back to a previous state in its navigation trajectory.<n>This mechanism gives the model the flexibility to directly control the search process, leading to an effective and efficient web navigation method.
  arXiv  Detail & Related papers  (2025-04-16T05:41:20Z)
• Reinforcement learning informed evolutionary search for autonomous systems testing [15.210312666486029]
  We propose augmenting the evolutionary search (ES) with a reinforcement learning (RL) agent trained using surrogate rewards derived from domain knowledge. In our approach, known as RIGAA, we first train an RL agent to learn useful constraints of the problem and then use it to produce a certain part of the initial population of the search algorithm. We evaluate RIGAA on two case studies: maze generation for an autonomous ant robot and road topology generation for an autonomous vehicle lane keeping assist system.
  arXiv  Detail & Related papers  (2023-08-24T13:11:07Z)
• A suite of diagnostic metrics for characterizing selection schemes [45.74830585715129]
  We introduce DOSSIER, a diagnostic suite initially composed of eight handcrafted metrics. These metrics are designed to empirically measure specific capacities for exploitation, exploration, and their interactions. We apply DOSSIER to six popular selection schemes: truncation, tournament, fitness sharing, lexicase, nondominated sorting, and novelty search.
  arXiv  Detail & Related papers  (2022-04-29T01:05:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.