Lune

ACL Findings2024

ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs

Lei Sun, Zhengwei Tao, Youdi Li, Hiroshi Arakawa

Abstract

The integration of Large Language Models (LLMs) and knowledge graphs (KGs) has achieved remarkable success in various natural language processing tasks. However, existing methodologies that integrate LLMs and KGs often navigate the task-solving process solely based on the LLM's analysis of the question, overlooking the rich cognitive potential inherent in the vast knowledge encapsulated in KGs. To address this, we introduce Observation-Driven Agent (ODA), a novel AI agent framework tailored for tasks involving KGs. ODA incorporates KG reasoning abilities via global observation, which enhances reasoning capabilities through a cyclical paradigm of observation, action, and reflection. Confronting the exponential explosion of knowledge during observation, we innovatively design a recursive observation mechanism. Subsequently, we integrate the observed knowledge into the action and reflection modules. Through extensive experiments, ODA demonstrates state-of-theart performance on several datasets, notably achieving accuracy improvements of 12.87% and 8.9%. Our code and data are available on https://github.com/lanjiuqing64/KGdata.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
  • Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling cites Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains
  • Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling cites Language Models are Few-Shot Learners
  • Self-Consistency Improves Chain of Thought Reasoning in Language Models cites Language Models are Few-Shot Learners
  • G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
  • Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning cites Language Models are Few-Shot Learners
  • Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation cites G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
  • Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
  • Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation cites Language Models are Few-Shot Learners
  • Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains cites G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
  • Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and OpportunitiesChuangtao Ma, Yongrui Chen, Tianxing Wu, Arijit Khan et al.EMNLP 2025 · 6 citations
  2. Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward ModelingShiqi Yan, Yubo Chen, Ruiqi Zhou, Zhengxi Yao et al.ICLR 2026 · 3 citations
  3. Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented GenerationMufei Li, Siqi Miao, Pan LiICLR 2025
  4. Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed ChainsKun Li, Tianhua Zhang, Xixin Wu, Hongyin Luo et al.ACL 2025

Builds on13

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations
  3. Reasoning on Graphs: Faithful and Interpretable Large Language Model ReasoningLinhao Luo, Yuan-Fang Li, Gholamreza Haffari, Shirui PanICLR 2024 · 499 citations
  4. G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question AnsweringXiaoxin He, Yijun Tian, Yifei Sun, Nitesh V. Chawla et al.NeurIPS 2024 · 384 citations
  5. Crosslingual Generalization through Multitask FinetuningNiklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts et al.ACL 2023 · 319 citations

Related papers

  1. KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge GraphJinhao Jiang, Kun Zhou, Xin Zhao, Yang Song et al.ACL 2025
  2. Reflection on Knowledge Graph for Large Language Models ReasoningYigeng Zhou, Wu Li, Yifan Lu, Jing Li et al.ACL Findings 2025 · 8 citations
  3. SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge GraphsBen Liu, Jihai Zhang, Fangquan Lin, Cheng Yang et al.WWW 2025 · 21 citations
  4. Exploration-and-Thinking: Agentic Reasoning over Knowledge Graphs via an LLM-RL Synergized FrameworkYi Xia, Gang Zhou, Jing Chen, Xiaohui Chen et al.SIGIR 2026
  5. Thought-Action Graph Reasoning: Faithful and Efficient Reasoning of Large Language Models via Reusing Past ExperienceZhixiao Qi, Feng Huang, Yunqi Zhang, Shijie Zhang et al.ACL Findings 2026
Dusk over the sea between two cliffs drawn in fine vertical lines