hiw3c AI 日报
arXiv cs.AI/CL/LG 网页快照

Cogentic:用于自动证据发现的多智能体规划

原文标题 · Cogentic: Multi-Agent Orchestration for Automated Proof Discovery

作者:杨蔡、维尼特·古普塔、江彦晨|我们介绍了Cogentic,这是一种多代理工具,用于自动发现开放研究问题的证据。虽然前沿语言模型可以在一次尝试中产生强大的数学思想,但对于需要探索多个竞争猜想、克服微妙的技术障碍并在很长一段时间内保持中间进展的开放问题,单次尝试生成通常不足以

来源:arXiv cs.AI/CL/LG · arxiv.org

正文为英文,可一键机器翻译(仅首次需要等待)

Computer Science > Artificial Intelligence

Title: Cogentic: Multi-Agent Orchestration for Automated Proof Discovery

Abstract: We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often insufficient for open problems that require exploring multiple competing conjectures, overcoming subtle technical obstructions, and retaining intermediate progress over a long horizon. Cogentic addresses these challenges through an iterative prove--verify loop in which an orchestrator allocates a population of independent provers across distinct proof directions, subjects their output to adversarial verification by several specialized components, and promotes confirmed intermediate results into a persistent verified ledger that later rounds build on. The harness is designed to be able to solve research-level math and theoretical computer science problems. Using Gemini as the base model, Cogentic produced novel results on five open problems across online learning, auction theory, and mechanism design. Each result was independently verified by domain experts and is developed in full in companion papers. We list these results, and new ones as they are verified, at this https URL .

Submission history

Access Paper:

Current browse context:

References & Citations

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .