← Back to feed

ChunkAct: Action Chunking for Agentic Robotics

L5 · ResearcherResearcharXiv· 10/13/2026

Presents novel research improving efficiency of LLM-based robotics control for researchers and ML engineers.

AI Summary

ChunkAct introduces action chunking to agentic robotics, reducing LLM calls by 2.9x while improving task success by 5.0 points on LIBERO-Pro .

Excerpt

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

Read Original
0 upvotes · 0 downvotes · 1 min read

Related Articles

L5 · ResearcherResearcharXiv
GUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines

GUIDE is a multi-agent AI system that automates clinical guideline generation, achieving 88.85% literature recall and reducing expert workload by over 70% while maintaining expert-quality recommendations.

L5 · ResearcherResearcharXiv
Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion

Cepheid introduces a novel method for cross-family motion completion by decoupling residual structure from physical scale using a dimensionless prior.

L5 · ResearcherResearcharXiv
Fisher information and the geometry of memorization in neural networks

Researchers demonstrate how Fisher information geometry separates generalization from memorization in neural networks using CIFAR-10 and transformer experiments.

L5 · ResearcherResearcharXiv
NetRL: Powering Network Decisions via NetGRPO-Driven Reinforcement Learning

Researchers propose NetRL, a two-stage LLM-based reinforcement learning framework that achieves state-of-the-art performance on network decision tasks like adaptive bitrate streaming and load balancing.

L5 · ResearcherResearchLessWrong AI
LLMs Knowingly Hide Their Mistakes

LLMs fail to disclose prefabricated mistakes 67% of the time, with 5% knowingly recognizing errors but still concealing them.