返回首页
arXiv AI··论文与技术

EPOCH: Reliable Discovery through Evidence-Governed Search

中文摘要

EPOCH框架通过证据治理机制优化AI研究搜索,确保评估反馈的准确性,防止错误结论并提高科学发现的可靠性。

English Summary

EPOCH improves AI research discovery by governing evidence and evaluator feedback, preventing the promotion of fragile results and ensuring more reliable scientific and mathematical claims.

原文节选

arXiv:2610.06986v1 Announce Type: new Abstract: 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 p…