Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning

TL;DR

This paper introduces a neuro-symbolic framework that improves the reliability of code-based task planning in embodied agents by incorporating symbolic verification and interactive validation, significantly enhancing success rates in complex environments.

Contribution

The paper presents a novel neuro-symbolic framework that integrates symbolic verification and interactive validation into code generation for embodied task planning, improving reliability and success rates.

Findings

Improves task success rates by 46.2% over baselines

Achieves over 86.8% executability of task actions

Enhances code grounding in dynamic, partially observable environments

Abstract

Recent advances in large language models (LLMs) have enabled the automatic generation of executable code for task planning and control in embodied agents such as robots, demonstrating the potential of LLM-based embodied intelligence. However, these LLM-based code-as-policies approaches often suffer from limited environmental grounding, particularly in dynamic or partially observable settings, leading to suboptimal task success rates due to incorrect or incomplete code generation. In this work, we propose a neuro-symbolic embodied task planning framework that incorporates explicit symbolic verification and interactive validation processes during code generation. In the validation phase, the framework generates exploratory code that actively interacts with the environment to acquire missing observations while preserving task-relevant states. This integrated process enhances the grounding of generated code, resulting in improved task reliability and success rates in complex environments. We evaluate our framework on RLBench and in real-world settings across dynamic, partially observable scenarios. Experimental results demonstrate that our framework improves task success rates by 46.2% over Code-as-Policies baselines and attains over 86.8% executability of task-relevant actions, thereby enhancing the reliability of task planning in dynamic environments.