Abstract

Vision-language models (VLMs) have demonstrated remarkable capabilities in robotic planning, particularly for long-horizon tasks that require a holistic understanding of the environment for task decomposition. Existing methods typically rely on prior environmental knowledge or carefully designed task-specific prompts, making them struggle with dynamic scene changes or unexpected task conditions, e.g., a robot attempting to put a carrot in the microwave but finds the door was closed. Such challenges underscore two critical issues: adaptability and efficiency. To address them, in this work, we propose an adaptive multi-agent planning framework, termed REMAC, that enables efficient, scene-agnostic multi-robot long-horizon task planning and execution through continuous reflection and self-evolution. REMAC incorporates two key modules: a self-reflection module performing pre-condition and post-condition checks in the loop to evaluate progress and refine plans, and a self-evolvement module dynamically adapting plans based on scene-specific reasoning. It offers appealing benefits: 1) Robots can keep reflecting on potential planning errors and adapting the plan based on task-specific insights. 2) After iterations, a robot can call another one to coordinate tasks in parallel, maximizing the task execution efficiency. To validate REMAC's effectiveness, we build a multi-agent environment for long-horizon robot manipulation and navigation based on RoboCasa, featuring 4 task categories with 27 task styles and 50+ different objects. Based on it, we further benchmark state-of-the-art reasoning models, including DeepSeek-R1, o3, QwQ, Qwen3, and Grok3. Extensive experiments demonstrate REMAC's superiority by boosting average success rates by 40% and execution efficiency by 52.7% over the single robot baseline without any task-specific prompting or fine-tuning in initial planning.

Approach

Left: Self-Reflection: Before the execution of subtask i, the VLM verifies the pre-conditions to determine whether the plan for subtask i is executable given the observation after completing subtask i - 1. If not, this indicates an error in the initial planning, and the system engages in a reflection process to identify the cause of this error, which is subsequently stored in the reflection database. Following the execution of subtask i, the VLM verifies the post-conditions to assess whether the subtask was successfully executed, given the observation after executing the current task. If not, the system initiates a retry of the subtask.

Right: Self-Evolvement: Upon sequential completion of all subtasks, the reflection database—containing accumulated pre-condition-check analysis and last-iteration plan serves as the foundation for generating initial plans for subsequent iterations. This knowledge-augmented process iteratively refines planning logic, yielding an optimized initial plan with feasibility and efficiency for future iterations.

Real-World Demo

We demonstrate the REMAC multi-agent collaboration system in real-world scenarios for long-horizon robot manipulation tasks.

Experiments