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

2026-03-09 · Hai Xia, Carla P. Gomes, Bart Selman, Stefan Szeider arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.08322

Code (0)

등록된 구현이 없습니다.

VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation

2025-12-12 · Adewale Akinfaderin, Shreyas Subramanian arxiv

Financial AI systems suffer from a critical blind spot: while Retrieval-Augmented Generation (RAG) excels at finding relevant documents, language models still generate calculation errors and regulatory violations during …

Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents

2026-04-01 · Thanh Luong Tuan, Abhijit Sanyal arxiv

Enterprise adoption of Large Language Models (LLMs) is constrained by hallucination, domain drift, and the inability to enforce regulatory compliance at the reasoning level. We present a neurosymbolic architecture implem…

CausalPulse: An Industrial-Grade Neurosymbolic Multi-Agent Copilot for Causal Diagnostics in Smart Manufacturing

2026-03-31 · Chathurangi Shyalika, Utkarshani Jaimini, Cory Henson, Amit Sheth arxiv

Modern manufacturing environments demand real-time, trustworthy, and interpretable root-cause insights to sustain productivity and quality. Traditional analytics pipelines often treat anomaly detection, causal inference,…

Anomaly Detection Causal Inference

The AI Research Assistant: Promise, Peril, and a Proof of Concept

2026-02-26 · Tan Bui-Thanh arxiv

Can artificial intelligence truly contribute to creative mathematical research, or does it merely automate routine calculations while introducing risks of error? We provide empirical evidence through a detailed case stud…

The Neurosymbolic Frontier of Nonuniform Ellipticity: Formalizing Sharp Schauder Theory via Topos-Theoretic Reasoning Models

2026-02-11 · Suyash Mishra arxiv

This white paper presents a critical synthesis of the recent breakthrough in nonuniformly elliptic regularity theory and the burgeoning field of neurosymbolic large reasoning models (LRMs). We explore the resolution of t…