Mendel Gödel Machine：基于比较进化的递归自改进编码代理

AI 摘要

Mendel Gödel Machine (MGM) 是一种递归自改进编码代理，通过多轨迹突变和跨谱系杂交加速收敛并提升性能。该研究在理论上证明了新策略在加性适应度景观模型下的优势，并在 SWE-bench 和 Polyglot 基准上验证了其性能、效率和泛化能力的提升。

正文节选

Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution Abstract Mendel Gödel Machine improves self-improving coding agents by using multi-trajectory mutations and cross-lineage hybridization to accelerate convergence and boost performance. Self-improving coding agents that iteratively rewrite their own source code have demonstrated impressive performance on coding tasks. However, existing solutions generally derive self-modification from a single failure trajector

发布时间：—

抓取时间：2026-08-12 11:02

来源机构：Hugging Face