PulseAugur
中
实时 20:13:55
English(EN) Viva La Vida: Verification and Accumulation Failures in Multi-Agent Proof Search

多智能体系统在数学和软件验证中推进自动证明发现 · 跟踪 5 个来源

研究人员开发了先进的多智能体系统,用于形式数学和软件验证中的自动证明发现。其中一个框架 FORALL-LEAN-AGENT 通过结合隔离的工作空间和独立的证明检查来增强可审计推理,提高了成功率并降低了 VeriSoftBench 和 PutnamBench 等基准测试的成本。另一个系统 Cogentic 利用带有协调器和专用智能体的迭代证明-验证循环来解决开放研究问题,使用 Gemini 等模型在复杂的数学和理论计算机科学挑战中展示了新颖的结果。 AI

影响 多智能体系统在自动证明发现方面的这些进展,通过使人工智能能够解决复杂的开放性问题,有可能显著加速形式数学和理论计算机科学领域的研究。

排序理由 该集群包含多篇学术论文,详细介绍了人工智能辅助定理证明和自动证明发现的新方法和框架。

在 arXiv cs.MA (Multiagent) 阅读 →

AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →

多智能体系统在数学和软件验证中推进自动证明发现 · 跟踪 5 个来源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含多篇学术论文,详细介绍了人工智能辅助定理证明和自动证明发现的新方法和框架。
Source corroboration
6 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
paper, product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
52 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [6]

  1. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Noah Han ·

    Viva La Vida:多智能体证明搜索中的验证和累积失败

    When an agentic prover works on an open problem, there is no proof assistant to fall back on: its verifier and lemma library are ultimately language models judging model outputs. We instrumented such a system end to end and analyzed $51{,}754$ traced observations across three ful…

  2. arXiv cs.AI TIER_1 English(EN) · Naing Oo Lwin ·

    FORALL-LEAN-AGENT 用于形式数学和软件验证中的可审计推理

    arXiv:2610.00885v1 Announce Type: cross Abstract: Coding agents increasingly automate Lean proof development, but successful compilation alone does not establish that a candidate proves the intended statement under acceptable assumptions. We present FORALL-LEAN-AGENT, a frontend-…

  3. arXiv cs.AI TIER_1 English(EN) · Jules Viennot, Guillaume Baudart, Marc Lelarge ·

    构建Agent/Prover接口:用于Rocq和Lean中成本高效定理证明的进化工具设计

    arXiv:2609.39544v1 Announce Type: new Abstract: Recent achievements in AI-assisted mathematics require intensive interaction of agents with proof assistants to generate machine-checked proof certificates. Agents interact with proof assistants such as Rocq or Lean through an inter…

  4. arXiv cs.AI TIER_1 English(EN) · Yang Cai, Vineet Gupta, Yanchen Jiang, Christopher Liaw, Aranyak Mehta, Grigoris Velegkas, Di Wang ·

    Cogentic:自动化证明发现的多智能体编排

    arXiv:2609.40324v1 Announce Type: new 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…

  5. X — Omar Sanseviero (HF research) TIER_1 English(EN) · omarsar0 ·

    Google Research 发布的关于多智能体证明发现的重磅论文。

    Banger paper from Google Research on multi-agent proof discovery. (bookmark it) It's really interesting to see this emerging multi-agent pattern: not enforcing too much execution structure and pairing it with dedicated agents for advising and verification. I think it is https:…

  6. dev.to — LLM tag TIER_1 English(EN) · mech.app ·

    Cogentic:自动化证明发现的多智能体编排

    <p>Single-shot LLM generation breaks down on open research problems. You need to explore competing conjectures, overcome technical obstructions, and retain intermediate progress over long horizons. Cogentic is a multi-agent harness that solves this coordination problem for automa…