Metraipolis › archive › dc_9114bfe03bb2
EPOCH: Reliable Discovery through Evidence-Governed Search — arXiv:2610.06986
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.06986
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:18:14.071Z
- SHA-256 of the archived text
085831cdcf2c7329d31d5b14d39cea7ce94291c0bd74c82d93ffc1f22448042f- Stable URL of this page
https://metraipolis.com/documento/dc_9114bfe03bb2
How to cite
EPOCH: Reliable Discovery through Evidence-Governed Search — arXiv:2610.06986 — arXiv (en), https://arxiv.org/abs/2610.06986 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9114bfe03bb2 (Metraipolis archive dc_9114bfe03bb2, sha256 085831cdcf2c7329d31d5b14d39cea7ce94291c0bd74c82d93ffc1f22448042f)
BibTeX
@misc{dc9114bfe03bb2,
title = {EPOCH: Reliable Discovery through Evidence-Governed Search — arXiv:2610.06986},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.06986},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9114bfe03bb2; sha256 085831cdcf2c7329d31d5b14d39cea7ce94291c0bd74c82d93ffc1f22448042f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06986. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI research agents are increasingly used to search over programs, mathematical constructions, and proofs. However, existing systems typically optimize evaluator feedback without adequately governing how that feedback is interpreted, challenged, and reused. As a result, promising but fragile candidates can be promoted as discoveries, while benchmark improvements, finite certificates, and theorem-level claims are too easily conflated. We introduce EPOCH, an evidence-governed architecture designed to close this gap. EPOCH implements an evidence-governed discovery loop by combining explicit task contracts, typed memory, active falsification, admission checks, and independent replay, so that each candidate is evaluated against the strength and scope of the claim it supports. EPOCH achieves state-of-the-art aggregate performance on AlgoTune, substantially exceeding the strongest baseline in mean normalized score (0.65 vs. 0.53), and attains the highest mean score on the internal Math14 suite (0.57). It further shows favorable held-out behavior under official-test replay and leads the descriptive aggregate on AgentHPO. Across ten discovery problems, EPOCH delivers substantial task-specific advances, including improved executable constructions, optimized algorithms, counterexamples, and proof-supported results. These advances demonstrate its ability to convert search into concrete progress across mathematical and computational domains. Together, the results suggest that evidence governance is a necessary step toward AI research agents that produce not only stronger solutions, but also more trustworthy scientific discoveries. 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/2610.06986 — 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 2026-10-07T11:15:24.463Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).