G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning

• URL: http://arxiv.org/abs/2505.18499v2
• Date: Tue, 03 Jun 2025 07:21:57 GMT
• Title: G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
• Authors: Xiaojun Guo, Ang Li, Yifei Wang, Stefanie Jegelka, Yisen Wang,
• Abstract summary: Reinforcement Learning (RL) on synthetic graph-theoretic tasks can significantly scale graph reasoning abilities.<n>With RL on Erdos, G1 obtains substantial improvements in graph reasoning, where our finetuned 3B model even outperforms Qwen2.5-72B-Instruct (24x size)<n>Our findings offer an efficient, scalable path for building strong graph reasoners by finetuning LLMs with RL on graph-theoretic tasks.
• Score: 58.73279333365234
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although Large Language Models (LLMs) have demonstrated remarkable progress, their proficiency in graph-related tasks remains notably limited, hindering the development of truly general-purpose models. Previous attempts, including pretraining graph foundation models or employing supervised fine-tuning, often face challenges such as the scarcity of large-scale, universally represented graph data. We introduce G1, a simple yet effective approach demonstrating that Reinforcement Learning (RL) on synthetic graph-theoretic tasks can significantly scale LLMs' graph reasoning abilities. To enable RL training, we curate Erd\~os, the largest graph reasoning dataset to date comprising 50 diverse graph-theoretic tasks of varying difficulty levels, 100k training data and 5k test data, all drived from real-world graphs. With RL on Erd\~os, G1 obtains substantial improvements in graph reasoning, where our finetuned 3B model even outperforms Qwen2.5-72B-Instruct (24x size). RL-trained models also show strong zero-shot generalization to unseen tasks, domains, and graph encoding schemes, including other graph-theoretic benchmarks as well as real-world node classification and link prediction tasks, without compromising general reasoning abilities. Our findings offer an efficient, scalable path for building strong graph reasoners by finetuning LLMs with RL on graph-theoretic tasks, which combines the strengths of pretrained LLM capabilities with abundant, automatically generated synthetic data, suggesting that LLMs possess graph understanding abilities that RL can elicit successfully. Our implementation is open-sourced at https://github.com/PKU-ML/G1, with models and datasets hosted on Hugging Face collections https://huggingface.co/collections/PKU-ML/g1-683d659e992794fc99618cf2 for broader accessibility.

Related papers

• Generalizable LLM Learning of Graph Synthetic Data with Reinforcement Learning [38.485929062532925]
  We propose to unlock generalizable learning of graph synthetic data with reinforcement learning.<n>We first design solution-based and process-based rewards for synthetic graph problems.<n>Experiments demonstrate that our RL recipe leads to statistically significant improvement on 5 datasets.
  arXiv  Detail & Related papers  (2025-06-01T05:39:56Z)
• Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models [59.98982735197465]
  Tokenized Graph Learning Models (TGLMs) convert graphs into ordered token lists for scalable processing.<n>TGLMs rely on hand-designed token lists and their adaptability to diverse graph learning scenarios remains unexplored.<n>We propose Learnable Graph Token List (LGTL), a plug-and-play module to replace hand-designed token lists in TGLMs.
  arXiv  Detail & Related papers  (2025-05-19T06:25:33Z)
• Compile Scene Graphs with Reinforcement Learning [69.36723767339001]
  Next-token prediction is the fundamental principle for training large language models (LLMs)<n>We introduce R1-SGG, a multimodal LLM (M-LLM) initially trained via supervised fine-tuning (SFT) on the scene graph dataset.<n>We design a set of graph-centric rewards, including three recall-based variants -- Hard Recall, Hard Recall+Relax, and Soft Recall.
  arXiv  Detail & Related papers  (2025-04-18T10:46:22Z)
• A Hierarchical Language Model For Interpretable Graph Reasoning [47.460255447561906]
  We introduce Hierarchical Language Model for Graph (HLM-G), which employs a two-block architecture to capture node-centric local information and interaction-centric global structure. The proposed scheme allows LLMs to address various graph queries with high efficacy, efficiency, and robustness, while reducing computational costs on large-scale graph tasks. Comprehensive evaluations across diverse graph reasoning and real-world tasks of node, link, and graph-levels highlight the superiority of our method.
  arXiv  Detail & Related papers  (2024-10-29T00:28:02Z)
• What Do LLMs Need to Understand Graphs: A Survey of Parametric Representation of Graphs [69.48708136448694]
  Large language models (LLMs) are reorganizing in the AI community for their expected reasoning and inference abilities.<n>We believe this kind of parametric representation of graphs, graph laws, can be a solution for making LLMs understand graph data as the input.
  arXiv  Detail & Related papers  (2024-10-16T00:01:31Z)
• How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension [53.6373473053431]
  This work introduces a benchmark to assess large language models' capabilities in graph pattern tasks.<n>We have developed a benchmark that evaluates whether LLMs can understand graph patterns based on either terminological or topological descriptions.<n>Our benchmark encompasses both synthetic and real datasets, and a variety of models, with a total of 11 tasks and 7 models.
  arXiv  Detail & Related papers  (2024-10-04T04:48:33Z)
• LLaGA: Large Language and Graph Assistant [73.71990472543027]
  Large Language and Graph Assistant (LLaGA) is an innovative model to handle the complexities of graph-structured data. LLaGA excels in versatility, generalizability and interpretability, allowing it to perform consistently well across different datasets and tasks. Our experiments show that LLaGA delivers outstanding performance across four datasets and three tasks using one single model.
  arXiv  Detail & Related papers  (2024-02-13T02:03:26Z)
• GraphLLM: Boosting Graph Reasoning Ability of Large Language Model [7.218768686958888]
  GraphLLM is a pioneering end-to-end approach that integrates graph learning models with Large Language Models. Our empirical evaluations across four fundamental graph reasoning tasks validate the effectiveness of GraphLLM. The results exhibit a substantial average accuracy enhancement of 54.44%, alongside a noteworthy context reduction of 96.45%.
  arXiv  Detail & Related papers  (2023-10-09T16:42:00Z)
• Integrating Graphs with Large Language Models: Methods and Prospects [68.37584693537555]
  Large language models (LLMs) have emerged as frontrunners, showcasing unparalleled prowess in diverse applications. Merging the capabilities of LLMs with graph-structured data has been a topic of keen interest. This paper bifurcates such integrations into two predominant categories.
  arXiv  Detail & Related papers  (2023-10-09T07:59:34Z)
• Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPT [10.879701971582502]
  We aim to develop a large language model (LLM) with the reasoning ability on complex graph data. Inspired by the latest ChatGPT and Toolformer models, we propose the Graph-ToolFormer framework to teach LLMs themselves with prompts augmented by ChatGPT to use external graph reasoning API tools.
  arXiv  Detail & Related papers  (2023-04-10T05:25:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.