arXiv：cs.AI· Bingxin Xu, Wenrui Bao, Xinxin Liu, Jiawei Zhou, Yuzhang Shang, Emilio Ferrara·· 22 小时前
ChunkAct：面向具身智能体的动作分块方法
ChunkAct: Action Chunking for Agentic Robotics
AI 导读
ChunkAct 将动作分块引入具身智能体机器人，在线单次调用即可启动一串链式原语自主执行、仅在失败时交还控制权，离线则把记忆编译为这些分块，使测试时无需记忆、LLM 计算量随决策数而非原语数增长。
正文
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.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.18874 [cs.RO] |
| (or arXiv:2610.18874v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18874 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bingxin Xu [view email]
[v1]
Tue, 13 Oct 2026 17:59:57 UTC (452 KB)
来源：arXiv：cs.AI · arxiv.org