Metraipolis › archive › dc_6debdf468b94

Coral Discovery: The Division of Cognitive Labor in Autonomous Research — arXiv:2610.33281

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33281
License (as archived)
CC0-1.0
Archived
2026-10-27T05:20:03.514Z
SHA-256 of the archived text
383ba54e379732df25a180f4fb5676d2258d08ff3328d01b0ab6a8b5ddfc41de
Stable URL of this page
https://metraipolis.com/documento/dc_6debdf468b94

How to cite

Coral Discovery: The Division of Cognitive Labor in Autonomous Research — arXiv:2610.33281 — arXiv (en), https://arxiv.org/abs/2610.33281 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6debdf468b94 (Metraipolis archive dc_6debdf468b94, sha256 383ba54e379732df25a180f4fb5676d2258d08ff3328d01b0ab6a8b5ddfc41de)
BibTeX
@misc{dc6debdf468b94,
  title = {Coral Discovery: The Division of Cognitive Labor in Autonomous Research — arXiv:2610.33281},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33281},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6debdf468b94; sha256 383ba54e379732df25a180f4fb5676d2258d08ff3328d01b0ab6a8b5ddfc41de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33281. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A research community is only as strong as the way it divides its cognitive labour. The philosopher Philip Kitcher argued that researchers should not all pursue the most promising approach. Credit rules, not a central plan, keep some of them on other lines. We bring this question to autonomous research, where Large Language Model agents improve programs against a deterministic grader. Agents that share only a score follow the leader and converge onto one approach. Coral Discovery gives the community a direction board. A verifier labels every attempt with a direction, the mechanism earning the score, and a method, one change within it. Per direction, the board tracks how much each eval improves the score, adds an exploration bonus for little-tried directions, prices the option of opening a new direction, and suggests how many agents each direction deserves. Credit is earned against a direction's own best, so a lagging direction keeps its agents. Agents finish their lines, then treat the board as advice. We test on nine tasks with the same model and budget, without grader access except for Kernel. Coral Discovery beats the strongest open autonomous multi-agent system on 6 tasks, ties on 1, and loses on 2. Against published numbers, it is best or tied on 4. It improves the reported Kernel result from 1103 to 1095 cycles and passes 1103 at eval 275, under half of the 596 used before. It sets a new Polyominoes state of the art, 91.78 against 87.0. Direction labels show that the leading scores rest on directions a score-only community never entered. Code will be released shortly.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.33281 — 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 2026-10-27T05:19:32.715Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).