Metraipolis › archive › dc_5862a5cee557

SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm — arXiv:2610.20431

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20431
License (as archived)
CC0-1.0
Archived
2026-10-15T20:02:29.442Z
SHA-256 of the archived text
e8e3833c31396c436154dee1e1a9813c289a53a24d0741dbc33d44a3fcc48731
Stable URL of this page
https://metraipolis.com/documento/dc_5862a5cee557

How to cite

SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm — arXiv:2610.20431 — arXiv (en), https://arxiv.org/abs/2610.20431 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5862a5cee557 (Metraipolis archive dc_5862a5cee557, sha256 e8e3833c31396c436154dee1e1a9813c289a53a24d0741dbc33d44a3fcc48731)
BibTeX
@misc{dc5862a5cee557,
  title = {SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm — arXiv:2610.20431},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20431},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5862a5cee557; sha256 e8e3833c31396c436154dee1e1a9813c289a53a24d0741dbc33d44a3fcc48731},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20431. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recursive self-improvement (RSI) in scientific research aims to improve agents' research capabilities through their own experimental experience. Scientific agent swarms can combine evidence and implementations from different research directions to guide their agents' subsequent experiments. However, poor experimental results can leave unclear whether to revise a hypothesis or its implementation, while overall program scores can hide components useful to other agents. To address these challenges, we introduce SwarmRSI, a framework that evolves scientific agent swarms for recursive self-improvement. We devise Feedback-Guided Swarm Mutation to refine hypotheses and their implementations using experimental feedback from other agents. We also propose Complementary Swarm Recombination to reuse retained hypotheses and complementary program components across agents, allowing partial results to support new research. Recursive Swarm Evolution integrates both mechanisms into a feedback loop, using new experimental evidence to guide subsequent research. Experiments on OpenProblems, NatureBench and MLE-Bench Lite demonstrate SwarmRSI's state-of-the-art (SOTA) performance. Further evaluations show that accumulated research experience improves performance on held-out tasks. Biologists also reproduce its programs for follow-up biological analyses.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.20431 — 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 2026-10-15T19:35:48.305Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).