{
  "id": 18382,
  "url": "https://arxiv.org/abs/2608.07645",
  "title": "Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution",
  "summary": "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 mutatio",
  "authors": "Changzhi Liu, Yilun Liu, Sikuan Yan, Volker Tresp, Yunpu Ma",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T20:00:00.000Z",
  "fetched_at": "2026-08-12T05:10:43.828Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/18382",
  "original_url": "https://arxiv.org/abs/2608.07645",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}