通过复用推理步骤加速具身思维链，提升机器人实时决策效率。
Fast ECoT: Efficient Embodied Chain-of-Thought via Thoughts Reuse
- 复用高层推理，减少重复计算
- 并行生成模块化推理，降低延迟7.5%
- 无需训练修改模型，适合现有机器人系统
具身思维链（ECoT）通过中间推理步骤提升了视觉-语言-动作（VLA）模型的性能与可解释性。然而，其串行自回归的标记生成带来了显著推理延迟，限制了实时部署。本文提出Fast ECoT，一种推理时加速方法，利用ECoT结构化和重复性特点，(1) 缓存并复用高层推理；(2) 并行生成模块化推理步骤。同时引入异步调度器，解耦推理与动作解码，进一步提升响应速度。Fast ECoT无需模型修改或额外训练，可无缝集成至现有VLA流程。在仿真（LIBERO）和真实机器人任务中，延迟最多降低7.5%，任务成功率和推理忠实度保持或提升，使ECoT策略更接近实际实时应用。
原文摘要 · Abstract (English)
Embodied Chain-of-Thought (ECoT) reasoning enhances vision-language-action (VLA) models by improving performance and interpretability through intermediate reasoning steps. However, its sequential autoregressive token generation introduces significant inference latency, limiting real-time deployment. We propose Fast ECoT, an inference-time acceleration method that exploits the structured and repetitive nature of ECoT to (1) cache and reuse high-level reasoning across timesteps and (2) parallelise the generation of modular reasoning steps. Additionally, we introduce an asynchronous scheduler that decouples reasoning from action decoding, further boosting responsiveness. Fast ECoT requires no model changes or additional training and integrates easily into existing VLA pipelines. Experiments in both simulation (LIBERO) and real-world robot tasks show up to a 7.5% reduction in latency with comparable or improved task success rate and reasoning faithfulness, bringing ECoT policies closer to practical real-time deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。