Metraipolis › archive › dc_05bc018325a2
AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding — arXiv:2610.05334
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05334
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:25:07.614Z
- SHA-256 of the archived text
3f784880355672f16d6180d999724cdfb3ea214c5b90b1725cc80ad6ba9bb10b- Stable URL of this page
https://metraipolis.com/documento/dc_05bc018325a2
How to cite
AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding — arXiv:2610.05334 — arXiv, https://arxiv.org/abs/2610.05334 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_05bc018325a2 (Metraipolis archive dc_05bc018325a2, sha256 3f784880355672f16d6180d999724cdfb3ea214c5b90b1725cc80ad6ba9bb10b)
BibTeX
@misc{dc05bc018325a2,
title = {AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding — arXiv:2610.05334},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05334},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_05bc018325a2; sha256 3f784880355672f16d6180d999724cdfb3ea214c5b90b1725cc80ad6ba9bb10b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05334. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Frameworks that use large language models for scientific discovery typically rely on a fixed, human-designed algorithm that decides what the model sees at each step, leaving the model only the role of proposer. The model knows nothing of the search beyond what it is shown. As models grow more capable, a question arises: does a search strategy chosen by a human before the run scale better than promoting the model from proposer to planner and letting it own the search? The Bitter Lesson suggests that choosing the strategy in advance is the kind of hand-designed structure that general methods eventually outscale. We introduce AgentDiscover, in which a coding agent plans the search using its context as working memory, runs experiments, and records every attempt in a database of ideas, candidates, and their relations. This database serves as the agent's long-term memory and is structured so that the selection rules of classical algorithms such as MAP-Elites and Monte Carlo tree search each reduce to a single query, which the agent is free to use, combine, or replace. A server maintains the database and steers the agent after every submission, keeping it on course over long runs. In our experiments, AgentDiscover is more cost-efficient than existing frameworks, reaching better scores at lower cost. On tasks in kernel engineering, biology, algorithm design, and mathematics, AgentDiscover outperforms prior discovery frameworks. Its programs would have placed first among human competitors in seven past AtCoder heuristic contests, and on eleven mathematical and systems optimization tasks it matches or exceeds every baseline that uses the same model. Our code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2610.05334 — 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 2026-10-06T05:24:05.576Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).