The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2610.27439v1 Announce Type: cross Abstract: Solving reasoning tasks supported on graphs typically requires providing a Language Reasoning Model (LRM) with a serialized description of the graph....
arXiv:2605.06462v2 Announce Type: replace Abstract: Progress in graph learning is hindered by benchmark practices that conflate the contributions of node features and graph structure, making it hard...
arXiv:2606. 15633v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown promise for reasoning over Text-Attributed Graphs (TAGs).
The paper introduces a two-stage diagnostic evaluation to assess the structural reliability of reasoning graphs used in large language models for tasks like multi-hop question answering. Stage 1 examines how graph reliability depends on topology, prompt design, and model family, while Stage 2 evaluates the impact of graph errors on uncertainty estimation. Findings show that graph-based computation is vulnerable to upstream errors, offers limited benefit as prompt context alone, but improves confidence-based answer discrimination and enables node-level diagnostics.
arXiv:2604. 12503v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios.
arXiv:2606. 15633v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown promise for reasoning over Text-Attributed Graphs (TAGs).