Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models

arXiv:2608.12391v1 Announce Type: cross Abstract: Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programmatically generated, structurally controlled, and naturally scaled to long-input settings. However, existing graph reasoning benchmarks have limited coverage of data complexity, rely heavily on manual construction, and lack unified evaluation across text-based and code-based reasoning modes. To address these limitations, we propose {ataset}, a five-stage extit{semi-automatic} framework for constructing complex graph reasoning benchmarks. It expands benchmark coverage along five dimensions: extit{Graph Size}, extit{Task Complexity}, extit{Task Description}, extit{Graph Loading}, and extit{Task Source}. The framework uses an LLM-based data generator to automatically produce task descriptions, graph data, reference solutions, graph-loading scripts, question forms, and evaluation scripts, while retaining human validation at key quality-control stages. Based on it, we construct a benchmark with 202 tasks and evaluate LLMs under text-based, code-based, and augmented reasoning settings. Experiments show that the complexity dimensions reveal model limitations that are less visible in existing benchmarks; existing fine-tuned models struggle to generalize to GraphGym, whereas retrieval-augmented methods show scenario-dependent adaptability, improving textual reasoning but not consistently improving coding reasoning. These findings suggest that ours serves as a challenging and diagnostic benchmark for graph reasoning and provides empirical guidance for future enhancement methods. Code and dataset will be published soon.

Source: arXiv cs.AI | 2026-08-14

Related