Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment

• URL: http://arxiv.org/abs/2608.23691v1
• Date: Mon, 24 Aug 2026 18:00:03 GMT
• Title: Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment
• Abstract summary: We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue a shared research goal.<n>We release all raw agent dialogues, proofs, and verification code, providing a transparent record of how these discoveries emerged.
• Score: 12.952007953406872
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue a shared research goal without a central coordinator or scripted pipeline. Agents choose their own research directions, conduct experiments, collaborate, and build a shared scientific literature. Across 12 construction problems from the AlphaEvolve catalogue and two additional case studies, the Station obtained results novel relative to the prior literature on five problems: a new infinite family of finite-field Kakeya sets, new exact 604-point kissing configurations in dimension 11, new records for the discretized Kakeya needle and sign uncertainty problems, and a substantially improved lower bound for Erdős's minimum-overlap problem. Agents also discovered novel infinite families for Book Ramsey numbers. Importantly, the agents produced not only numerical constructions but also theorems and analyses explaining how those constructions work, making the results more interpretable and easier for mathematicians to build upon. We release all raw agent dialogues, proofs, and verification code, providing a transparent record of how these discoveries emerged.

Related papers

• From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier [109.93387172162984]
  We argue that the next leap in AI4Math systems requires a decisive shift from predefined problem-solvers to research agents.<n>We provide a systematic review of the field, covering datasets, auto-formalization, and proof synthesis.
  arXiv  Detail & Related papers  (2026-07-08T17:46:36Z)
• Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries [35.87396515951979]
  We present EinsteinArena, an agent-native platform for open distributed research and discovery.<n>As of May 2026, agents on EinsteinArena have discovered 12 new state-of-the-art results better than any previous human or AI solutions.
  arXiv  Detail & Related papers  (2026-06-09T04:25:28Z)
• LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization [104.06650149974585]
  We present LeanMarathon, a multi-agent harness for reliable research-level Lean autoformalization.<n>Four contract-scoped agents construct, audit, prove, and repair this blueprint.<n>We evaluate LeanMarathon on two recent research papers spanning four Erds problems.
  arXiv  Detail & Related papers  (2026-06-03T20:09:39Z)
• Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery [51.70607714288616]
  Science Earth is a planet-scale scientific runtime in which any capability can connect to any other.<n>Its underlying EACN protocol lets capabilities discover one another, negotiate task ownership, and adjudicate across incompatible evidentiary standards.<n>Two runs validate this under structurally distinct conditions.
  arXiv  Detail & Related papers  (2026-05-31T16:05:41Z)
• The Last Human-Written Paper: Agent-Native Research Artifacts [106.47848184955576]
  We introduce the Agent-Native Research Artifact (ARA), a protocol that replaces the narrative paper with a machine-executable research package.<n>Three mechanisms support the ecosystem: a Live Research Manager that captures decisions and dead ends during ordinary development; an ARA Compiler that translates legacy PDFs and repos into ARAs; and an ARA-native review system that automates objective checks so human reviewers can focus on significance, novelty, and taste.
  arXiv  Detail & Related papers  (2026-04-27T16:23:09Z)
• Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design [39.02605479431633]
  We study mathematical discovery through the lens of neurosymbolic reasoning, where an AI agent powered by a large language model (LLM)<n>The main result of this human-AI collaboration is a tight lower bound on the imbalance of Latin squares for the notoriously difficult case $n equiv 1 pmod3$.
  arXiv  Detail & Related papers  (2026-03-09T12:42:56Z)
• Towards Autonomous Mathematics Research [48.29504087871558]
  We introduce Aletheia, a math research agent that iteratively generates, verifies, and revises solutions end-to-end in natural language.<n>Specifically, Aletheia is powered by an advanced version of Gemini Deep Think for challenging reasoning problems.<n>We demonstrate Aletheia from Olympiad problems to PhD-level exercises and most notably, through several distinct milestones in AI-assisted mathematics research.
  arXiv  Detail & Related papers  (2026-02-10T18:50:15Z)
• Accelerating Scientific Research with Gemini: Case Studies and Common Techniques [105.15622072347811]
  Large language models (LLMs) have opened new avenues for accelerating scientific research.<n>We present a collection of case studies demonstrating how researchers have successfully collaborated with advanced AI models.
  arXiv  Detail & Related papers  (2026-02-03T18:56:17Z)
• The Station: An Open-World Environment for AI-Driven Discovery [14.556758955830796]
  We introduce the STATION, an open-world multi-agent environment that models a miniature scientific ecosystem.<n>Agents in the Station can engage in long scientific journeys that include reading papers from peers, formulating hypotheses, submitting code, performing analyses, and publishing results.<n>Experiments demonstrate that AI agents in the Station achieve new state-of-the-art performance on a wide range of benchmarks, spanning from mathematics to computational biology to machine learning.
  arXiv  Detail & Related papers  (2025-11-09T10:13:00Z)
• Learning from {\L}ukasiewicz and Meredith: Investigations into Proof Structures (Extended Version) [4.111899441919164]
  This paper studies global features in selected problems and their proofs. The studied problems are of the wide-spread form of "axiom(s) and rule(s) imply goal(s)"
  arXiv  Detail & Related papers  (2021-04-28T09:09:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.