ActionReasoning: Robot Action Reasoning in 3D Space with LLM for Robotic Brick Stacking

TL;DR

This paper introduces ActionReasoning, an LLM-based framework for robotic brick stacking that uses explicit physics-aware reasoning to produce stable actions, demonstrating improved generalization and reduced domain-specific coding.

Contribution

The paper presents a novel multi-agent LLM framework that integrates physical priors for explicit action reasoning in robotic manipulation tasks.

Findings

Enables stable brick placement in a simulated environment.

Shifts effort from low-level coding to high-level prompting.

Shows potential for broader generalization in robotic tasks.

Abstract

Classical robotic systems typically rely on custom planners designed for constrained environments. While effective in restricted settings, these systems lack generalization capabilities, limiting the scalability of embodied AI and general-purpose robots. Recent data-driven Vision-Language-Action (VLA) approaches aim to learn policies from large-scale simulation and real-world data. However, the continuous action space of the physical world significantly exceeds the representational capacity of linguistic tokens, making it unclear if scaling data alone can yield general robotic intelligence. To address this gap, we propose ActionReasoning, an LLM-driven framework that performs explicit action reasoning to produce physics-consistent, prior-guided decisions for robotic manipulation. ActionReasoning leverages the physical priors and real-world knowledge already encoded in Large Language Models (LLMs) and structures them within a multi-agent architecture. We instantiate this framework on a tractable case study of brick stacking, where the environment states are assumed to be already accurately measured. The environmental states are then serialized and passed to a multi-agent LLM framework that generates physics-aware action plans. The experiments demonstrate that the proposed multi-agent LLM framework enables stable brick placement while shifting effort from low-level domain-specific coding to high-level tool invocation and prompting, highlighting its potential for broader generalization. This work introduces a promising approach to bridging perception and execution in robotic manipulation by integrating physical reasoning with LLMs.