HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents
This work addresses the challenge of making embodied agents more autonomous and reliable in task execution, representing an incremental improvement over existing multimodal language model systems.
The paper tackled the problem of adaptive monitoring and repair of code policies for embodied agents by introducing HyCodePolicy, a hybrid language-based control framework that integrates code synthesis, geometric grounding, perceptual monitoring, and iterative repair, resulting in significantly improved robustness and sample efficiency of robot manipulation policies.
Recent advances in multimodal large language models (MLLMs) have enabled richer perceptual grounding for code policy generation in embodied agents. However, most existing systems lack effective mechanisms to adaptively monitor policy execution and repair codes during task completion. In this work, we introduce HyCodePolicy, a hybrid language-based control framework that systematically integrates code synthesis, geometric grounding, perceptual monitoring, and iterative repair into a closed-loop programming cycle for embodied agents. Technically, given a natural language instruction, our system first decomposes it into subgoals and generates an initial executable program grounded in object-centric geometric primitives. The program is then executed in simulation, while a vision-language model (VLM) observes selected checkpoints to detect and localize execution failures and infer failure reasons. By fusing structured execution traces capturing program-level events with VLM-based perceptual feedback, HyCodePolicy infers failure causes and repairs programs. This hybrid dual feedback mechanism enables self-correcting program synthesis with minimal human supervision. Our results demonstrate that HyCodePolicy significantly improves the robustness and sample efficiency of robot manipulation policies, offering a scalable strategy for integrating multimodal reasoning into autonomous decision-making pipelines.