# Huxley-G"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine

arXiv: https://arxiv.org/abs/2510.21614 · HTML: https://mlsanity.com/paper/2510.21614/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 48 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-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, 18 of 18)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation](https://mlsanity.com/paper/2310.02304/) (2023)
- [SWE-bench Goes Live!](https://mlsanity.com/paper/2505.23419/) (2025)
- [A Self-Improving Coding Agent](https://mlsanity.com/paper/2504.15228/) (2025)
- [Discovering Evolution Strategies via Meta-Black-Box Optimization](https://mlsanity.com/paper/2211.11260/) (2022)
- [Simple regret for infinitely many armed bandits](https://mlsanity.com/paper/1505.04627/) (2015)
- [G"odel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement](https://mlsanity.com/paper/2410.04444/) (2024)
- [Eliminating Meta Optimization Through Self-Referential Meta Learning](https://mlsanity.com/paper/2212.14392/) (2022)
- [Monte-Carlo Tree Search by Best Arm Identification](https://mlsanity.com/paper/1706.02986/) (2017)
- [Training Learned Optimizers with Randomly Initialized Learned Optimizers](https://mlsanity.com/paper/2101.07367/) (2021)
- [Self-Modification of Policy and Utility Function in Rational Agents](https://mlsanity.com/paper/1605.03142/) (2016)
- [Bounded Recursive Self-Improvement](https://mlsanity.com/paper/1312.6764/) (2013)

## Built on by (most cited first, 30 of 53)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?](https://mlsanity.com/paper/2511.13646/) (2025)
- [MemEvolve: Meta-Evolution of Agent Memory Systems](https://mlsanity.com/paper/2512.18746/) (2025)
- [SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios](https://mlsanity.com/paper/2512.18470/) (2025)
- [Toward Training Superintelligent Software Agents through Self-Play SWE-RL](https://mlsanity.com/paper/2512.18552/) (2025)
- [From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws](https://mlsanity.com/paper/2606.06324/) (2026)
- [AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning](https://mlsanity.com/paper/2511.19304/) (2025)
- [The Red Queen G"odel Machine: Co-Evolving Agents and Their Evaluators](https://mlsanity.com/paper/2606.26294/) (2026)
- [Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch](https://mlsanity.com/paper/2603.24647/) (2026)
- [AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces](https://mlsanity.com/paper/2608.23041/) (2026)
- [DarwinX: Evolving Agent Harnesses Through Natural Selection](https://mlsanity.com/paper/2608.07545/) (2026)
- [RRSI: Regularized Recursive Self-Improvement of Agent Harnesses](https://mlsanity.com/paper/2609.24972/) (2026)
- [Harnessing Agentic Evolution](https://mlsanity.com/paper/2605.13821/) (2026)
- [Recursive self-improvement of AI research agents](https://mlsanity.com/paper/2609.26457/) (2026)
- [Training AI Scientists to Replicate Research](https://mlsanity.com/paper/2608.13331/) (2026)
- [AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design](https://mlsanity.com/paper/2608.13560/) (2026)
- [RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments](https://mlsanity.com/paper/2609.15364/) (2026)
- [Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses](https://mlsanity.com/paper/2608.08466/) (2026)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization](https://mlsanity.com/paper/2602.04811/) (2026)
- [DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations](https://mlsanity.com/paper/2605.24539/) (2026)
- [EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines](https://mlsanity.com/paper/2601.09465/) (2026)
- [AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive](https://mlsanity.com/paper/2605.11518/) (2026)
- [On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification](https://mlsanity.com/paper/2608.18066/) (2026)
- [Self Improvement via Fast Tree-search](https://mlsanity.com/paper/2609.19526/) (2026)
- [Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents](https://mlsanity.com/paper/2609.11677/) (2026)
- [Beyond the Node: Clade-level Selection for Efficient MCTS in Automatic Heuristic Design](https://mlsanity.com/paper/2602.00549/) (2026)
- [Pioneer Agent: Continual Improvement of Small Language Models in Production](https://mlsanity.com/paper/2604.09791/) (2026)
- [Evolving Ensemble of Agents](https://mlsanity.com/paper/2605.09018/) (2026)
- [Knowledge-Centric Self-Improvement](https://mlsanity.com/paper/2607.19592/) (2026)

## Abstract (arXiv)

Recent studies operationalize self-improvement through coding agents that edit their own codebases. They grow a tree of self-modifications through expansion strategies that favor higher software engineering benchmark performance, assuming that this implies more promising subsequent self-modifications. However, we identify a mismatch between the agent's self-improvement potential (metaproductivity) and its coding benchmark performance, namely the Metaproductivity-Performance Mismatch. Inspired by Huxley's concept of clade, we propose a metric (CMP) that aggregates the benchmark performances of the descendants of an agent as an indicator of its potential for self-improvement. We show that, in our self-improving coding agent development setting, access to the true CMP is sufficient to simulate how the G"odel Machine would behave under certain assumptions. We introduce the Huxley-G"odel Machine (HGM), which, by estimating CMP and using it as guidance, searches the tree of self-modifications. On SWE-bench Verified and Polyglot, HGM outperforms prior self-improving coding agent development methods while using fewer allocated CPU hours. Last but not least, HGM demonstrates strong transfer to other coding datasets and large language models. The agent optimized by HGM on SWE-bench Verified with GPT-5-mini and evaluated on SWE-bench Lite with GPT-5 achieves human-level performance, matching the best officially checked results of human-engineered coding agents. Our code is publicly available at https://github.com/metauto-ai/HGM.