GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning
Chen Li, Sijie Cheng, Yuelin Zhang, Junxi Li, Maozhi Huang, Yang Liu, Wenbing Huang
cs.AI, cs.RO
Submitted: 2026-08-08
Updated: 2026-08-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks
- Online Continual Learning For Interactive Instruction Following Agents
- CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios
- FILM: Following Instructions in Language with Modular Methods
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Prompter: Utilizing Large Language Model Prompting for a Data Efficient Embodied Instruction Following
- OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following
- Inner Monologue: Embodied Reasoning through Planning with Language Models
- SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning
- Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering
- You Only Look at Screens: Multimodal Chain-of-Action Agents
- ToolRL: Reward is All Tool Learning Needs
- What is the Alignment Objective of GRPO?
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
- One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems