Model Releases
ChunkAct: Action Chunking for Agentic Robotics
arXiv:2610.18874v1 Announce Type: cross Abstract: Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-action
arXiv:2610.18874v1 Announce Type: cross 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.
Related
- See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model
- Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation
- OrthoSkillVLA: Continual Skill Learning via Gradient-Informed Skill Subspace Adaptation
- RAIN: Robotic Task Generalization with Region-Aware Interaction Networks
- DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
Source: arXiv cs.CV | 2026-10-14