LLM Reasoning with Graphs

LLM: Large Language Model

Overview

The field studies how large language models can use graphs to represent relationships, retrieve evidence, and organize multi-step reasoning, especially when answers depend on several connected facts. Common approaches include retrieving paths or subgraphs from knowledge graphs for tasks such as WebQSP and CWQ question answering, giving models tools to navigate graphs, and integrating graph neural networks, symbolic rules, or executable code with language-model reasoning. Other work represents reasoning itself as a chain, tree, or directed graph, and trains models with supervised traces or reinforcement learning to explore paths and verify intermediate steps. These methods can improve multi-hop accuracy and make evidence easier to inspect, but benchmarks also show that graph information is not always used correctly; handling incomplete or noisy evidence, scaling to larger graphs, and demonstrating genuine structural understanding remain open challenges.

Latest papers

CardsList

227 papers25 papers in the last four weeks, down 14% on the four weeks before. 0.2% of all new papers.

  1. Interactive Structured Environment Scaling for Large Language Model Agentic Reasoning

    Nov 15, 2026Peng Yu, Luoyi Fu, Xinbing Wang +1RL for Language Model ReasoningRL for LLM Agents

  2. Chain of Physics: Supporting Fault Diagnosis with Engineering-Inspired Large Language Model Reasoning

    Nov 10, 2026Wenqi Zhou, Leonardo Baldo, Kai Goebel +1Industrial Fault DiagnosisLLM Reasoning with Graphs

  3. Enhancing Multi-Step Chemical Mechanism Prediction with Graph-Guided Preference Data

    Nov 9, 2026Yu Zhang, Ruijie Yu, Xuelin Zhao +5Chemical Reaction PredictionLLM Reasoning with Graphs

  4. Typed-Centrality Grounding for Agentic GraphRAG: A Symbolic Approach for Agentic Reasoning

    Nov 6, 2026Rosario Napoli, Antonio Celesti, Massimo Villari +1Graph Retrieval-Augmented GenerationLLM Reasoning with Graphs

  5. Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation

    Nov 5, 2026Ali Sarabadani, Kheirolah Rahsepar Fard, Tahereh JeiraniLLM Reasoning with GraphsLanguage Model Reasoning Evaluation

  6. Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair

    Nov 5, 2026Tung-Wei Lin, Gabe Fierro, Han Li +3Knowledge GraphsRetrieval-Augmented Reasoning

  7. Graph-Mediated Large Language Model Systems in the Agentic Era: Reasoning, Knowledge, Retrieval, Execution, and Coordination

    Nov 4, 2026Haihui Liu, Yang Chen, Zice Qiu +5LLM Reasoning with GraphsGraph-Based Agent Memory

  8. GraphNIAH: A Benchmark for Long-Context Reasoning over Real-World Graphs

    Oct 30, 2026Minh-Nam Tran, Abulhair SaparovLong-Context Reasoning in Language ModelsLanguage Model Reasoning Evaluation

  9. ImplicitHop: Evaluating knowledge integration across context and memory

    Oct 30, 2026Alexander Detkov, Dashiel Karish, Matthew Oleynikov +1Knowledge Retrieval in Language ModelsLanguage Model Reasoning Evaluation

  10. Prospector: learning a compact graph traversal policy for scientific reasoning

    Oct 27, 2026Haiqian Yang, Markus J. BuehlerLLM Reasoning with GraphsScientific Reasoning in Language Models

  11. Evolve on Graph: Self-Evolving Knowledge Graph Reasoning without Question Annotations

    Oct 26, 2026Zongyuan Sun, Shuai Zhao, Ke Shu +8LLM Reasoning with GraphsKnowledge Graph Question Answering

  12. UniGFM-RAG: Unify Graph Foundation Models and Large Language Models for End-to-End Retrieval and Reasoning

    Oct 26, 2026Zicheng Zhao, Linhao Luo, Zongji Yu +4Graph Retrieval-Augmented GenerationLLM Reasoning with Graphs

  13. On the Token Collapse Phenomenon in Textual Graph Soft Prompting

    Oct 22, 2026Andrea Giuseppe Di Francesco, Rishabh Jain, Franco Maria Nardini +3Graph Prompt LearningLLM Reasoning with Graphs

  14. Multi-Token Prediction and Alternative Tokenization Improve Learning Latent Multi-Hop Graph Search at Scale

    Oct 22, 2026Arvid Frydenlund, FuTe Wong, Katherine Lambert +1LLM Reasoning with GraphsGraph-Based Planning

  15. Constraint Reasoning and Large Language Models Join Forces: Providing Contrastive Explanations for Real-World Optimisation-Based Applications

    Oct 22, 2026Roger X. Lera-Leri, Filippo Bistaffa, Athina Georgara +1Constraint-Guided Reasoning in Language ModelsCounterfactual Explanations

  16. Better Reasoning, Not Just Bigger Models: A Structure-Grounded Framework for Efficient and Reliable Inference

    Oct 22, 2026Amirhossein Aghaei, Liangyan Li, Shiyi Yang +2LLM Reasoning with GraphsLLM Grounding

  17. Scaling Graph Reasoning in Language Models with Learnable Graph Positional Encodings

    Oct 20, 2026Javier Porras-Valenzuela, Arush Arora, Alejandro RibeiroLLM Reasoning with GraphsGraph Positional Encoding

  18. Diagnostic Analysis for Large Language Model Reasoning

    Oct 19, 2026Xinyu Liu, Dongqi Fu, Jun WuLanguage Model Reasoning EvaluationLLM Reasoning with Graphs

  19. GraphEvoResearcher: A Cost-Matched Mechanism Analysis of Explicit Reasoning Graphs in Training-Free Self-Reflection

    Oct 19, 2026Suxing Liu, Byungwon Min, Zhijian Zheng +1Multi-Hop QALLM Self-Refinement

  20. Bridging Concepts: Multi-Agent Reasoning over Scientific Concept Graphs for High-Impact Research Prediction

    Oct 18, 2026Donggyu Yoon, Minsung Hwang, Juneha Baek +2Knowledge GraphsLLM Reasoning with Graphs

  21. Euler: Towards Human-Centered Multi-Agent Mathematical Discovery

    Oct 14, 2026Qiuyu Chen, Qi Wang, Liang Xu +3AI-Assisted Mathematical DiscoveryAutonomous Research Agents

  22. Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces

    Oct 13, 2026Haotian Liu, Yingjian Chen, Xiaohang Xu +4LLM Self-CorrectionReasoning Verification