Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design

2026-03-09

AI Summary

This study addresses the problem of establishing a tight lower bound on the imbalance of Latin squares in combinatorial design when $n \equiv 1 \pmod{3}$. The authors propose a human–AI collaborative paradigm for mathematical discovery, integrating large language models, symbolic computation, constraint solving, simulated annealing, and formal verification in Lean 4. By introducing a new class of combinatorial objects termed “near-perfect permutations,” they derive and formally verify the tight lower bound of $4n(n{-}1)/9$ on the imbalance. This work not only achieves a substantive advance in pure mathematics but also demonstrates the effectiveness—and limitations—of multi-model collaboration in constructive exploration and rigorous validation.

Technology Category

Constraint Satisfaction and Optimization: Other Foundations of Constraint SatisfactionSearch and Optimization: Combinatorial OptimizationKnowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasetsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingGraph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

We study mathematical discovery through the lens of neurosymbolic reasoning, where an AI agent powered by a large language model (LLM), coupled with symbolic computation tools, and human strategic direction, jointly produced a new result in combinatorial design theory. The main result of this human-AI collaboration is a tight lower bound on the imbalance of Latin squares for the notoriously difficult case $n \equiv 1 \pmod{3}$. We reconstruct the discovery process from detailed interaction logs spanning multiple sessions over several days and identify the distinct cognitive contributions of each component. The AI agent proved effective at uncovering hidden structure and generating hypotheses. The symbolic component consists of computer algebra, constraint solvers, and simulated annealing, which provides rigorous verification and exhaustive enumeration. Human steering supplied the critical research pivot that transformed a dead end into a productive inquiry. Our analysis reveals that multi-model deliberation among frontier LLMs proved reliable for criticism and error detection but unreliable for constructive claims. The resulting human-AI mathematical contribution, a tight lower bound of $4n(n{-}1)/9$, is achieved via a novel class of near-perfect permutations. The bound was formally verified in Lean 4. Our experiments show that neurosymbolic systems can indeed produce genuine discoveries in pure mathematics.

Problem

• combinatorial design
• Latin squares
• imbalance
• lower bound
• mathematical discovery

Innovation

• neurosymbolic reasoning
• mathematical discovery
• combinatorial design
• Latin squares
• human-AI collaboration