Discovering mathematical concepts through a multi-agent system

• URL: http://arxiv.org/abs/2603.04528v1
• Date: Wed, 04 Mar 2026 19:13:36 GMT
• Title: Discovering mathematical concepts through a multi-agent system
• Authors: Daattavya Aggarwal, Oisin Kim, Carl Henrik Ek, Challenger Mishra,
• Abstract summary: We present a new multi-agent model for computational mathematical discovery.<n>Our system, conceived with research in mind, poses its own conjectures and then attempts to prove them.<n>We claim that the optimisation of the right combination of local processes can lead to surprisingly well-aligned notions of mathematical interestingness.
• Score: 3.820195410658766
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mathematical concepts emerge through an interplay of processes, including experimentation, efforts at proof, and counterexamples. In this paper, we present a new multi-agent model for computational mathematical discovery based on this observation. Our system, conceived with research in mind, poses its own conjectures and then attempts to prove them, making decisions informed by this feedback and an evolving data distribution. Inspired by the history of Euler's conjecture for polyhedra and an open challenge in the literature, we benchmark with the task of autonomously recovering the concept of homology from polyhedral data and knowledge of linear algebra. Our system completes this learning problem. Most importantly, the experiments are ablations, statistically testing the value of the complete dynamic and controlling for experimental setup. They support our main claim: that the optimisation of the right combination of local processes can lead to surprisingly well-aligned notions of mathematical interestingness.

Related papers

• 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)
• Can Neural Networks Learn Small Algebraic Worlds? An Investigation Into the Group-theoretic Structures Learned By Narrow Models Trained To Predict Group Operations [4.635620949885696]
  We explore the extent to which narrow models trained to solve a fixed mathematical task learn broader mathematical structure that can be extracted by a researcher or other AI system.<n>We describe a suite of tests designed to assess whether the model captures significant group-theoretic notions such as the identity element, commutativity, or subgroups.<n>Our results suggest that in some cases the representations of even small neural networks can be used to distill interesting abstract structure from new mathematical objects.
  arXiv  Detail & Related papers  (2026-01-29T01:18:22Z)
• Mathematical exploration and discovery at scale [1.2341209649260667]
  AlphaEvolve is a generic evolutionary coding agent that proposes, tests, and refines algorithmic solutions to scientific and practical problems.<n>To demonstrate its breadth, we considered a list of 67 problems spanning mathematical analysis, combinatorics, geometry, and number theory.<n>In some instances, AlphaEvolve is also able to generalize results for a finite number of input values into a formula valid for all input values.
  arXiv  Detail & Related papers  (2025-11-03T16:04:07Z)
• Newton to Einstein: Axiom-Based Discovery via Game Design [55.30047000068118]
  We propose a game design framework in which scientific inquiry is recast as a rule-evolving system.<n>Unlike conventional ML approaches that operate within fixed assumptions, our method enables the discovery of new theoretical structures.
  arXiv  Detail & Related papers  (2025-09-05T18:59:18Z)
• In Reverie Together: Ten Years of Mathematical Discovery with a Machine Collaborator [0.0]
  We present four open conjectures in graph theory generated by the automated conjecturing system textttTxGraffiti.<n>Each conjecture is concise, grounded in natural graph invariants, and empirically validated across hundreds of graphs.<n>We aim to inspire both human mathematicians and AI systems to engage with them--not only to solve them, but to reflect on what it means when machines participate meaningfully in the creative process of mathematical thought.
  arXiv  Detail & Related papers  (2025-07-23T00:49:32Z)
• On the Fundamental Impossibility of Hallucination Control in Large Language Models [0.0]
  Impossibility Theorem: no LLM performing non-trivial knowledge aggregation can simultaneously achieve truthful knowledge representation, semantic information conservation, and revelation of relevant knowledge.<n>We prove this by modeling inference as an auction of ideas, where distributed components compete to influence responses using encoded knowledge.<n>We show that hallucination and imagination are mathematically identical, and both violate at least one of the four essential properties.
  arXiv  Detail & Related papers  (2025-06-04T23:28:39Z)
• Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models [76.6028674686018]
  We introduce thought-tracing, an inference-time reasoning algorithm to trace the mental states of agents.<n>Our algorithm is modeled after the Bayesian theory-of-mind framework.<n>We evaluate thought-tracing on diverse theory-of-mind benchmarks, demonstrating significant performance improvements.
  arXiv  Detail & Related papers  (2025-02-17T15:08:50Z)
• Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning [85.635988711588]
  We argue that enhancing the capabilities of large language models requires a paradigm shift in the design of mathematical datasets.<n>We advocate for mathematical dataset developers to consider the concept of "motivated proof", introduced by G. P'olya in 1949, which can serve as a blueprint for datasets that offer a better proof learning signal.<n>We provide a questionnaire designed specifically for math datasets that we urge creators to include with their datasets.
  arXiv  Detail & Related papers  (2024-12-19T18:55:17Z)
• LeanAgent: Lifelong Learning for Formal Theorem Proving [85.39415834798385]
  We present LeanAgent, a novel lifelong learning framework for formal theorem proving.<n>LeanAgent continuously generalizes to and improves on ever-expanding mathematical knowledge.<n>It generates formal proofs for 155 theorems across 23 diverse Lean repositories.
  arXiv  Detail & Related papers  (2024-10-08T17:11:24Z)
• A Mathematical Model of the Hidden Feedback Loop Effect in Machine Learning Systems [44.99833362998488]
  We introduce a repeated learning process to jointly describe several phenomena attributed to unintended hidden feedback loops. A distinctive feature of such repeated learning setting is that the state of the environment becomes causally dependent on the learner itself over time. We present a novel dynamical systems model of the repeated learning process and prove the limiting set of probability distributions for positive and negative feedback loop modes.
  arXiv  Detail & Related papers  (2024-05-04T17:57:24Z)
• math-PVS: A Large Language Model Framework to Map Scientific Publications to PVS Theories [10.416375584563728]
  This work investigates the applicability of large language models (LLMs) in formalizing advanced mathematical concepts. We envision an automated process, called emphmath-PVS, to extract and formalize mathematical theorems from research papers.
  arXiv  Detail & Related papers  (2023-10-25T23:54:04Z)
• A Survey of Deep Learning for Mathematical Reasoning [71.88150173381153]
  We review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade. Recent advances in large-scale neural language models have opened up new benchmarks and opportunities to use deep learning for mathematical reasoning.
  arXiv  Detail & Related papers  (2022-12-20T18:46:16Z)

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.