# Graphormer-Guided Task Planning: Beyond Static Rules with LLM Safety Perception

arXiv: https://arxiv.org/abs/2503.06866 · HTML: https://mlsanity.com/paper/2503.06866/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [Wayformer: Motion Forecasting via Simple & Efficient Attention Networks](https://mlsanity.com/paper/2207.05844/) (2022)
- [TidyBot: Personalized Robot Assistance with Large Language Models](https://mlsanity.com/paper/2305.05658/) (2023)
- [RoCo: Dialectic Multi-Robot Collaboration with Large Language Models](https://mlsanity.com/paper/2307.04738/) (2023)
- [Vision-Language Models as Success Detectors](https://mlsanity.com/paper/2303.07280/) (2023)
- [AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents](https://mlsanity.com/paper/2401.12963/) (2024)
- [Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents](https://mlsanity.com/paper/2309.09919/) (2023)
- [Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks](https://mlsanity.com/paper/2405.01534/) (2024)
- [Prompt a Robot to Walk with Large Language Models](https://mlsanity.com/paper/2309.09969/) (2023)
- [SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models](https://mlsanity.com/paper/2409.19471/) (2024)
- [Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning](https://mlsanity.com/paper/2411.06920/) (2024)
- [Trajectory Prediction for Autonomous Driving using Agent-Interaction Graph Embedding](https://mlsanity.com/paper/2410.23298/) (2024)
- [GNN-based Decentralized Perception in Multirobot Systems for Predicting Worker Actions](https://mlsanity.com/paper/2501.04193/) (2025)

## Built on by (most cited first, 4 of 4)

- [A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?](https://mlsanity.com/paper/2505.10924/) (2025)
- [Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects](https://mlsanity.com/paper/2507.21407/) (2025)
- [APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight](https://mlsanity.com/paper/2505.13921/) (2025)
- [NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning](https://mlsanity.com/paper/2605.09387/) (2026)

## Abstract (arXiv)

Recent advancements in large language models (LLMs) have expanded their role in robotic task planning. However, while LLMs have been explored for generating feasible task sequences, their ability to ensure safe task execution remains underdeveloped. Existing methods struggle with structured risk perception, making them inadequate for safety-critical applications where low-latency hazard adaptation is required. To address this limitation, we propose a Graphormer-enhanced risk-aware task planning framework that combines LLM-based decision-making with structured safety modeling. Our approach constructs a dynamic spatio-semantic safety graph, capturing spatial and contextual risk factors to enable online hazard detection and adaptive task refinement. Unlike existing methods that rely on predefined safety constraints, our framework introduces a context-aware risk perception module that continuously refines safety predictions based on real-time task execution. This enables a more flexible and scalable approach to robotic planning, allowing for adaptive safety compliance beyond static rules. To validate our framework, we conduct experiments in the AI2-THOR environment. The experiments results validates improvements in risk detection accuracy, rising safety notice, and task adaptability of our framework in continuous environments compared to static rule-based and LLM-only baselines. Our project is available at https://github.com/hwj20/GGTP