2026· Annual Meeting of the Association for Computational Linguistics· pp. 18936-18955· 2 citations· 130 references
Computer Science
TL;DR
This work presents the first systematic survey of graph-assisted LLMs from the perspective of how graph structures mitigate LLMs’ limitations, and introduces a taxonomy spanning Graph-Assisted Knowledge Augmentation, Graph-Assisted Reasoning and Planning, and Graph-Assisted LLM Collaboration.
Abstract
Large language models (LLMs) have made progress in knowledge-intensive tasks, reasoning and planning, and collaborative problem solving, yet they exhibit intrinsic limitations such as knowledge cutoff, single-threaded reasoning that hinders finer-grained branch and aggregation, and rigid collaboration mechanisms that struggle to coordinate specialized capabilities. Graphs, with their ability to represent relational knowledge and complex dependencies, offer a natural means to address these limitations: they provide structured, high-density knowledge for augmenting or correcting LLMs’ generation; enable revisitable inference by organizing intermediate steps as graphs; and support dynamic coordination among experts or agents in collaborative settings. Motivated by these developments, we present the first systematic survey of graph-assisted LLMs from the perspective of how graph structures mitigate LLMs’ limitations. We introduce a taxonomy spanning Graph-Assisted Knowledge Augmentation, Graph-Assisted Reasoning and Planning, and Graph-Assisted LLM Collaboration , and analyze representative methods, summarize common design patterns, and outline open challenges and future directions for advancing LLMs with graph-based enhancements. The collected papers are available in link here.
In machine reading comprehension (MRC) tasks that involve complex logical reasoning, graph structures are often regarded as a more suitable representation paradigm than plain text sequences, owing to their explicit structured semantic environment and strong relational inference capabilities. Nevertheless, most existing graph-based MRC models commonly suffer from incomplete node representations and sparse connectivity during graph construction. Moreover, these models typically devote most of their capacity to refining node features while comparatively overlooking the rich relational information encoded in edges. Such limitations significantly curb the potential of graph structures to support deep relational understanding and complex reasoning tasks. In light of this, this study proposes a Graph-Structured Collaborative Inference (GSCI) framework for the task of logical reading comprehension, which consists of three key modules: LLM-empowered logic-oriented graph construction, dual-stream collaborative graph modeling, and structure-aware answer prediction. Firstly, GSCI leverages an LLM to perform fine-grained semantic parsing, extracting abundant structured knowledge that constructs logic-oriented graph foundation for downstream inference. Secondly, a node–edge cooperative modeling mechanism is designed to jointly capture semantic information from nodes and relational signals from edges. Thirdly, the learned structured representations are integrated with textual representations to support candidate answer prediction. Finally, comprehensive experiments on two challenging logical reasoning benchmarks (ReClor and LogiQA) demonstrate that GSCI consistently outperforms existing baselines, providing strong empirical evidence of its effectiveness in logical reading comprehension tasks.
Zhuo Zhao, Zhiwen Xie, Guangyou Zhou et al.· IEEE Transactions on Audio,...· 0 citations
GABench is introduced, a comprehensive benchmark for agentic graph analysis that covers four graph analysis task categories: graph retrieval, graph theory, graph machine learning, and graph open-ended question answering and provides practical insights into the development and evaluation of LLM agents for graph analysis.
Jiarui Tan, Zhongjian Zhang, Yabo Guo et al.· 1 citation
OptGraph is the first optimization agentic workflow that introduces graph retrieval-augmented generation (GraphRAG) and first constructs reusable experience as a typed graph, capturing the relationships among modeling patterns, problem formalization, implementation details, and error corrections.
Xianchao Xiu, Jianhao Li, Huangyue Chen et al.· 1 citation
Experiments on three different domain tasks show that FKGLM can effectively integrate LLMs and large-scale knowledge graphs, leading to a significant enhancement in the reasoning capabilities of LLMs.
Yulin Zhou, Yongbin Qin, Chuan Lin· Journal of King Saud Univers...· 0 citations
A five-stage semi-automatic framework for constructing complex graph reasoning benchmarks that serves as a challenging and diagnostic benchmark for graph reasoning and provides empirical guidance for future enhancement methods is proposed.
Fali Wang, Ali Al-Lawati, Iliyas Bektas et al.· 0 citations