Research

Paper

AI LLM February 24, 2026

LogicGraph : Benchmarking Multi-Path Logical Reasoning via Neuro-Symbolic Generation and Verification

Authors

Yanrui Wu, Lingling Zhang, Xinyu Zhang, Jiayu Chang, Pengyu Li, Xu Jiang, Jingtao Hu, Jun Liu

Abstract

Evaluations of large language models (LLMs) primarily emphasize convergent logical reasoning, where success is defined by producing a single correct proof. However, many real-world reasoning problems admit multiple valid derivations, requiring models to explore diverse logical paths rather than committing to one route. To address this limitation, we introduce LogicGraph, the first benchmark aimed to systematically evaluate multi-path logical reasoning, constructed via a neuro-symbolic framework that leverages backward logic generation and semantic instantiation. This pipeline yields solver-verified reasoning problems formalized by high-depth multi-path reasoning and inherent logical distractions, where each instance is associated with an exhaustive set of minimal proofs. We further propose a reference-free evaluation framework to rigorously assess model performance in both convergent and divergent regimes. Experiments on state-of-the-art language models reveal a common limitation: models tend to commit early to a single route and fail to explore alternatives, and the coverage gap grows substantially with reasoning depth. LogicGraph exposes this divergence gap and provides actionable insights to motivate future improvements. Our code and data will be released at https://github.com/kkkkarry/LogicGraph.

Metadata

arXiv ID: 2602.21044
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-02-24
Fetched: 2026-02-25 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.21044v1</id>\n    <title>LogicGraph : Benchmarking Multi-Path Logical Reasoning via Neuro-Symbolic Generation and Verification</title>\n    <updated>2026-02-24T16:04:26Z</updated>\n    <link href='https://arxiv.org/abs/2602.21044v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.21044v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Evaluations of large language models (LLMs) primarily emphasize convergent logical reasoning, where success is defined by producing a single correct proof. However, many real-world reasoning problems admit multiple valid derivations, requiring models to explore diverse logical paths rather than committing to one route. To address this limitation, we introduce LogicGraph, the first benchmark aimed to systematically evaluate multi-path logical reasoning, constructed via a neuro-symbolic framework that leverages backward logic generation and semantic instantiation. This pipeline yields solver-verified reasoning problems formalized by high-depth multi-path reasoning and inherent logical distractions, where each instance is associated with an exhaustive set of minimal proofs. We further propose a reference-free evaluation framework to rigorously assess model performance in both convergent and divergent regimes. Experiments on state-of-the-art language models reveal a common limitation: models tend to commit early to a single route and fail to explore alternatives, and the coverage gap grows substantially with reasoning depth. LogicGraph exposes this divergence gap and provides actionable insights to motivate future improvements. Our code and data will be released at https://github.com/kkkkarry/LogicGraph.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-24T16:04:26Z</published>\n    <arxiv:comment>24 pages, 17 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Yanrui Wu</name>\n    </author>\n    <author>\n      <name>Lingling Zhang</name>\n    </author>\n    <author>\n      <name>Xinyu Zhang</name>\n    </author>\n    <author>\n      <name>Jiayu Chang</name>\n    </author>\n    <author>\n      <name>Pengyu Li</name>\n    </author>\n    <author>\n      <name>Xu Jiang</name>\n    </author>\n    <author>\n      <name>Jingtao Hu</name>\n    </author>\n    <author>\n      <name>Jun Liu</name>\n    </author>\n  </entry>"
}