Metraipolis › archive › dc_e968d4e5aa54
Recursa: Toward Recursively Self-Improving Foundation Model Systems — arXiv:2611.04035
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04035
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:37:40.495Z
- SHA-256 of the archived text
9fc5851dd20e558bc0ddbeb613b093bcbddaef71ffc1c6ed0470c496f0f53a59- Stable URL of this page
https://metraipolis.com/documento/dc_e968d4e5aa54
How to cite
Recursa: Toward Recursively Self-Improving Foundation Model Systems — arXiv:2611.04035 — arXiv (en), https://arxiv.org/abs/2611.04035 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e968d4e5aa54 (Metraipolis archive dc_e968d4e5aa54, sha256 9fc5851dd20e558bc0ddbeb613b093bcbddaef71ffc1c6ed0470c496f0f53a59)
BibTeX
@misc{dce968d4e5aa54,
title = {Recursa: Toward Recursively Self-Improving Foundation Model Systems — arXiv:2611.04035},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04035},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e968d4e5aa54; sha256 9fc5851dd20e558bc0ddbeb613b093bcbddaef71ffc1c6ed0470c496f0f53a59},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04035. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Foundation models in changing environments can encounter unfamiliar domain knowledge that their original training did not cover. However, new domains rarely provide large amounts of expert-created training data or reliable supervisory signals for further training. We introduce Recursa, a foundation model system that adapts to new domains by learning from its own experience without human experts or a stronger teacher model. Recursa uses a knowledge repository to store what it learns: domain-specific skills and instructions on when to apply them, along with memories of past task experiences and reflections on what to improve. Recursa bootstraps the repository from domain materials and then refines it through recursive self-improvement. It uses parallel learners to execute tasks and synthesize local improvements, then validates and merges the improvements into the knowledge repository. On Harvey LAB's Firm Knowledge benchmark, Recursa raises the all-pass rate on held-out test tasks from 30.0% to 55.0% with DeepSeek-V4.1-Flash and from 35.0% to 46.0% with Qwen3.8-Flash. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.04035 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T21:35:49.506Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).