ThinkAct：通过强化视觉潜在规划实现视觉-语言-动作推理
ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
AI总结：
本文提出ThinkAct双系统框架，通过强化视觉潜在规划连接多模态大语言模型的高层推理与低层动作执行，在具身AI任务中实现少样本适应、长时程规划与自我纠正。
摘要：
视觉-语言-动作（VLA）推理任务要求智能体理解多模态指令、执行长时程规划，并在动态环境中自适应地行动。现有方法通常以端到端方式训练VLA模型，直接将输入映射为动作而缺乏显式推理，这限制了其进行多步规划或适应复杂任务变化的能力。本文提出ThinkAct，一个双系统框架，通过强化视觉潜在规划桥接高层推理与低层动作执行。ThinkAct训练一个多模态大语言模型，在基于目标完成度和轨迹一致性的动作对齐视觉奖励的强化引导下生成具身推理计划。这些推理计划被压缩为视觉计划潜在表示，用于条件化下游动作模型，从而在目标环境中实现鲁棒的动作执行。在具身推理和机器人操作基准上的大量实验表明，ThinkAct能够在复杂的具身AI任务中实现少样本适应、长时程规划和自我纠正行为。
英文摘要：
Vision-language-action (VLA) reasoning tasks require agents to interpret multimodal instructions, perform long-horizon planning, and act adaptively in dynamic environments. Existing approaches typically train VLA models in an end-to-end fashion, directly mapping inputs to actions without explicit reasoning, which hinders their ability to plan over multiple steps or adapt to complex task variations. In this paper, we propose ThinkAct, a dual-system framework that bridges high-level reasoning with low-level action execution via reinforced visual latent planning. ThinkAct trains a multimodal LLM to generate embodied reasoning plans guided by reinforcing action-aligned visual rewards based on goal completion and trajectory consistency. These reasoning plans are compressed into a visual plan latent that conditions a downstream action model for robust action execution on target environments. Extensive experiments on embodied reasoning and robot manipulation benchmarks demonstrate that ThinkAct enables few-shot adaptation, long-horizon planning, and self-correction behaviors in complex embodied AI tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
