arXiv Machine Learning September 3, 2026 By Yanting Yang, Can Jin, Jinman Zhao, Jiahao Wu, Yang Zhou, Zhepeng Wang, Zhendong Wang, Mu Zhou, Dimitris N. Metaxas

Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents

Read the original on arXiv Machine Learning →

The paper introduces SPACE, a method for enabling large language model agents to emit variable-length action chunks in long-horizon tasks. By distilling chunk-boundary supervision from programmatic skills derived from successful trajectories, SPACE overcomes the tendency of agents to either act one step at a time or commit to overly long sequences. Experiments on ALFWorld and ScienceWorld demonstrate that SPACE raises success rates by 7.0%–31.3% and cuts LLM decision rounds by up to 78.9%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Sep 2

Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents

Large language model (LLM) agents for long-horizon interactive tasks typically follow a ReAct-style protocol, issuing one primitive action per LLM round. While this enables frequent replanning, it is...

llms rag agents reinforcement-learning

arXiv AI

Jun 10

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning

arXiv:2606. 10507v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-horizon agentic tasks.

By Juncheng Diao, Zhicong Lu, Peiguang Li, Yongwei Zhou, Changyuan Tian, Qingbin Li, Rongxiang Weng, Jingang Wang, Xunliang Cai

llms agents nlp reinforcement-learning benchmarks

arXiv Machine Learning

Sep 30

FlexiWorld: Learning and Planning via Flexible Action Chunks Across Multiple Time Scales

FlexiWorld is a JEPA-based latent world model that learns variable‑length action chunks across multiple time scales for goal‑directed planning. It jointly trains a causal action encoder and an autoregressive actor, using mixed‑span goal supervision and Student Forcing to reduce exposure bias. In experiments on four benchmarks, FlexiWorld with the Actor‑Residual Cross‑Entropy Method (ARCEM) achieves higher mean success rates than the strongest baseline and supports flexible planning chunk lengths without retraining.

By Shidu Ren, Qilin Gu, Zhenghao Ni, Junhan Sun, Jiaqi Wang, Damien Scieur, Yunze Liu

benchmarks safety

arXiv AI

Sep 30

Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks

arXiv:2609.36471v1 Announce Type: cross Abstract: World-Action Models (WAMs) improve robotic manipulation by conditioning action generation on predicted future observations, but future prediction add...

By Guoheng Sun, Chen Chen, Jin Wang, Ang Li, Teresa Lv

rag robotics efficiency

arXiv Machine Learning

Sep 30

Action Chunking Proximal Policy Optimization with Feedback Correction

arXiv:2609.36250v1 Announce Type: new Abstract: Action chunking provides temporal abstraction in reinforcement learning by selecting short action sequences instead of individual actions, but many exi...

By Sanghyun Hahn, Jonghyun Choi

rag reinforcement-learning robotics

arXiv Machine Learning

Aug 14

SEAR: Sample Efficient Action Chunking Reinforcement Learning

arXiv:2603. 01891v2 Announce Type: replace Abstract: Action chunking improves exploration and accelerates value propagation in long-horizon reinforcement learning, but naively applying off-policy methods to the temporally extended action space at reduced decision frequency offsets these gains, leading to poor sample efficiency.

By C. F. Maximilian Nagy, Onur Celik, Emiliyan Gospodinov, Florian Seligmann, Weiran Liao, Aryan Kaushik, Gerhard Neumann

llms rag reinforcement-learning robotics benchmarks

One email a morning, machine-written

Related stories

Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning

FlexiWorld: Learning and Planning via Flexible Action Chunks Across Multiple Time Scales

Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks

Action Chunking Proximal Policy Optimization with Feedback Correction

SEAR: Sample Efficient Action Chunking Reinforcement Learning