Metraipolis › archive › dc_3312ee8f5ccf

ADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization — arXiv:2610.30851

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30851
License (as archived)
CC0-1.0
Archived
2026-10-25T20:47:37.933Z
SHA-256 of the archived text
251aaa08383f003b761c2621c2eca500608ed8b960f7bb556fcc11ec3c59f09a
Stable URL of this page
https://metraipolis.com/documento/dc_3312ee8f5ccf

How to cite

ADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization — arXiv:2610.30851 — arXiv (en), https://arxiv.org/abs/2610.30851 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3312ee8f5ccf (Metraipolis archive dc_3312ee8f5ccf, sha256 251aaa08383f003b761c2621c2eca500608ed8b960f7bb556fcc11ec3c59f09a)
BibTeX
@misc{dc3312ee8f5ccf,
  title = {ADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization — arXiv:2610.30851},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30851},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3312ee8f5ccf; sha256 251aaa08383f003b761c2621c2eca500608ed8b960f7bb556fcc11ec3c59f09a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30851. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific discovery often requires identifying a small number of high-performing designs in vast, constrained search spaces. This is difficult when evaluations are costly, feasible solutions are sparse, parameters are strongly coupled, and physical constraints are strict. Recent AI for AI methods can automatically improve algorithms and optimization procedures. However, general purpose approaches are not designed around scientific priors, physical constraints, and limited evaluation budgets. We introduce ADAPT for Science, a multi-agent framework that treats scientific optimization as two coupled decisions: where to search and how to search. ADAPT uses historical designs to identify promising and diverse initial conditions, progressively concentrates computation on favorable search directions, and evolves the optimization procedure from execution feedback. We evaluate ADAPT on the design of gravitational wave detectors using a differentiable physics simulator and eight unseen detector topologies. Under matched scientific evaluation budgets, ADAPT achieves a mean loss of 0.204 +/- 0.101, reducing loss by 54.9% relative to the best classical optimizer and by 62.2% relative to the best general purpose agentic evolution baseline. ADAPT achieves the lowest loss on all unseen topologies among the evaluated baselines. ADAPT provides a step toward scientific optimization systems that continuously learn from prior experience and their own search outcomes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA); Optics (physics.optics).
Pagina del lavoro: https://arxiv.org/abs/2610.30851 — 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 2026-10-25T20:47:26.476Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).