mlsanityData to 7 Oct 2026

GCoder: Improving Large Language Model for Generalized Graph Problem Solving

arXiv 2410.19084 ↗First posted 24 Oct 2024cs.CLcited by 11

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated strong reasoning abilities, making them suitable for complex tasks such as graph computation. Traditional reasoning steps paradigm for graph problems is hindered by unverifiable steps, limited long-term reasoning, and poor generalization to graph variations. To overcome these limitations, we introduce GCoder, a code-based LLM designed to enhance problem-solving in generalized graph computation problems. Our method involves constructing an extensive training dataset, GraphWild, featuring diverse graph formats and algorithms. We employ a multi-stage training process, including Supervised Fine-Tuning (SFT) and Reinforcement Learning from Compiler Feedback (RLCF), to refine model capabilities. For unseen tasks, a hybrid retrieval technique is used to augment performance. Experiments demonstrate that GCoder outperforms GPT-4o, with an average accuracy improvement of 16.42% across various graph computational problems. Furthermore, GCoder efficiently manages large-scale graphs with millions of nodes and diverse input formats, overcoming the limitations of previous models focused on the reasoning steps paradigm. This advancement paves the way for more intuitive and effective graph problem-solving using LLMs. Code and data are available at here: https://github.com/Bklight999/WWW25-GCoder/tree/master.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 29 of its 51 references that are in the map. First posted on arXiv 24 Oct 2024.

Builds on

29 of 51 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasets23 Jun
  2. 2024Can LLM Graph Reasoning Generalize beyond Pattern Memorization?23 Jun
  3. 2024GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability7 Mar
  4. 2024GraphWiz: An Instruction-Following Language Model for Graph Problems25 Feb
  5. 2024InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment13 Feb
  6. 2023Can Language Models Solve Graph Problems in Natural Language?17 May

Other references · 23

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  4. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  5. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  6. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  7. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  8. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  9. 2023Augmented Language Models: a Surveycited by 398
  10. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  11. 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 271
  12. 2023GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarkingcited by 209
11 more
  1. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 75
  2. 2023Label-free Node Classification on Graphs with Large Language Models (LLMS)cited by 72
  3. 2024MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoningcited by 34
  4. 2024How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehensioncited by 30
  5. 2024VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Contextcited by 29
  6. 2023Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphscited by 23
  7. 2024Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Modelscited by 17
  8. 2023A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignmentcited by 16
  9. 2024Link Recommendation to Augment Influence Diffusion with Provable Guaranteescited by 5
  10. 2024Finding Densest Subgraphs with Edge-Color Constraintscited by 2
  11. 2024Local Centrality Minimization with Quality Guaranteescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 5.

11 papers.

  1. 2025ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generationcited by 27
  2. 2026Graph is a Substrate Across Data Modalitiescited by 13
  3. 2025Rethinking and Benchmarking Large Language Models for Graph Reasoningcited by 6
  4. 2025Large Language Models in Operations Research: Methods, Applications, and Challengescited by 4
  5. 2026DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAscited by 4
  6. 2025MA-GTS: A Multi-Agent Framework for Solving Complex Graph Problems in Real-World Applicationscited by 3
  7. 2026Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problemscited by 3
  8. 2025Improving LLMs' Generalized Reasoning Abilities by Graph Problemscited by 1
  9. 2025Harnessing Adaptive Topology Representations for Zero-Shot Graph Question Answeringcited by 1
  10. 2026GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RLcited by 0
  11. 2026GraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence Rubricscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
  2. 2024CodeGraph: Enhancing Graph Reasoning of LLMs with Code
  3. 2025Less is More: Learning Graph Tasks with Just LLMs
  4. 2026Are Large Language Models Suitable for Graph Computation? Progress and Prospects
  5. 2024Graph Reasoning with Large Language Models via Pseudo-code Prompting
  6. 2025Exploring Graph Learning Tasks with Pure LLMs: A Comprehensive Benchmark and Investigation
  7. 2025Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoning
  8. 2025Rewarding Graph Reasoning Process makes LLMs more Generalized Reasoners