外观
论文arXiv 2610.1887415 天前
ChunkAct：面向智能体机器人的动作分块
原文链接：ChunkAct: Action Chunking for Agentic Robotics（arXiv 2610.18874 · 发布日期：2026-10-13）
ChunkAct: Action Chunking for Agentic Robotics
ChunkAct通过将记忆编译为动作块，减少智能体机器人控制中的LLM调用，并在LIBERO-Pro上验证性能与效率提升。
核心要点
- 智能体机器人每个原语都需LLM基于完整历史推理，导致成本随原语数增长。
- ChunkAct在线用一次调用启动链式原语块，失败时才返回控制。
- 离线将记忆编译为动作块，测试时无需记忆，规划器只处理需推理的决策。
- 在LIBERO-Pro上成功率提高5.0点，LLM调用减少2.9倍。
验证范围与局限：验证范围仅为摘要所述的LIBERO-Pro。
英文摘要 (Abstract)
Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-action (VLA) tools under the guidance of a memory and thereby generalizes to new tasks without retraining. This generality comes at a steep price in efficiency. Every primitive requires a round of LLM reasoning over the full interaction history, so the cost of an episode grows with the number of primitives. We find this reasoning largely redundant: once a sub-goal is chosen, its primitives follow a routine already prescribed by memory. We present ChunkAct, which introduces action chunking to agentic robotics. Online, a single call launches a chunk of chained primitives, which executes autonomously and returns control only upon failure. Offline, ChunkAct compiles the memory into these chunks, so execution is memory-free at test time and the planner is reserved for decisions that require reasoning. LLM computation therefore scales with the number of decisions rather than the number of primitives. On LIBERO-Pro, ChunkAct improves task success by 5.0 points over the state of the art in agentic robotics while requiring 2.9x fewer LLM calls, 4.4x fewer input tokens, and 2.3x fewer output tokens.
作者：Bingxin Xu, Wenrui Bao, Xinxin Liu, Jiawei Zhou, Yuzhang Shang, Emilio Ferrara
来源
本页事实对应的公开页面，以原文为准。