# Mendel Gödel Machine：通过比较进化实现递归自改进的编码智能体

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-07 08:00
- AIHOT 分数：56
- AIHOT 链接：https://aihot.virxact.com/items/cmspi2an8040jromiwzg0c865
- 原文链接：https://arxiv.org/abs/2608.07645

## AI 摘要

Mendel Gödel Machine（MGM）通过递归改写自身源码实现自改进，在单轨迹克隆突变之外新增反应规范突变与跨谱系杂交两种策略，以同时利用多任务及同任务其他谱系轨迹。在加性适应度景观下，理论证明与仿真显示新策略收敛更快更优，SWE-bench 和 Polyglot 实验确认性能、效率与泛化能力一致提升。

## 正文

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 trajectory at a time, overlooking rich comparative signals available in the agent's expanding archive of past attempts. According to Mendelian principles of controlled inheritance, we introduce Mendel Gödel Machine (MGM). In addition to the general single-trajectory clonal mutation, MGM includes two new types of self-modification that better utilizes evidences accumulated: the reaction-norm mutation edits an agent based on its trajectories on multiple tasks simultaneously, and the cross-lineage hybridization edits an agent using the trajectory of a reference agent from another lineage on the same task. Under an additive fitness landscape model, we prove theoretically and demonstrate via controlled surrogate simulation that the new strategies facilitate a faster and better convergence over single-trajectory baselines. Experiments on SWE-bench and Polyglot confirm MGM's consistent improvement in performance, efficiency, and generalizability.