llm-kb
← Back to research
Paper

PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers

PAC-ACT is a reinforcement-learning post-training framework for pretrained Action Chunking Transformer policies, designed to improve reliability in precision industrial contact manipulation under pose perturbations and contact-force constraints. It addresses distribution shift in contact-rich tasks that behavior-cloned policies suffer from.

0 engagement·1 source·Fri, Jul 10, 2026, 04:42 PM
The paper proposes PAC-ACT, a post-training framework that applies actor-critic reinforcement learning to fine-tune Action Chunking Transformer policies. This approach aims to enhance robustness in contact-rich industrial tasks where behavior cloning alone leads to distribution shift. The method is evaluated on precision contact manipulation tasks, showing improved performance under pose perturbations and contact-force constraints.

Entities

reinforcement learning(concept)PAC-ACT(tool)Action Chunking Transformer(model)behavior cloning(concept)industrial contact manipulation(concept)

Related

PaperThu, Jul 9, 2026, 07:07 PM

FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space

FlowDAgger is a new method for adapting frozen generative robot policies using human interventions in latent space. It enables sample- and compute-efficient correction of failure modes outside the pretraining distribution without large-scale data collection or online RL.

0 engagement·1 source·arxiv
arXiv
PaperThu, Jul 9, 2026, 10:34 PM

CLAP paper proposes direct VLM-to-VLA adaptation to isolate semantic transfer

A new arXiv paper introduces CLAP, a method that converts pretrained vision-language models (VLMs) into vision-language-action models (VLAs) with minimal architectural changes, avoiding the distribution mismatch caused by predicting actions as bare numeric tokens. The approach aims to clarify how VLM capabilities transfer across model scales for robot control.

0 engagement·1 source·arxiv
arXiv
PaperThu, Jul 9, 2026, 06:00 PM

LLM/VLA models enable prompt-driven exploration in RL

A new research paper proposes using large language models (LLMs) and vision-language-action (VLA) models to drive exploration in reinforcement learning by modifying natural language prompts, which induce global behavioral changes beyond standard action noise. This approach could help policies escape weak local optima more effectively.

0 engagement·1 source·arxiv
arXiv
PaperFri, Jul 10, 2026, 07:16 AM

KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling

A new paper introduces KV-PRM, a process reward model that reuses KV-cache from the base model to avoid re-encoding entire trajectories, reducing scoring cost from quadratic to linear in sequence length. This enables efficient test-time scaling for long-context multi-agent systems.

0 engagement·1 source·arxiv
arXiv
PaperFri, Jul 10, 2026, 12:57 PM

Mach-Mind-4-Flash Technical Report Released: 35B MoE Model Matches 100B-Class Performance via Post-Training

A technical report on arxiv introduces Mach-Mind-4-Flash, a 35B-parameter Mixture-of-Experts model with 3B activated parameters. Through post-training optimization alone, it achieves performance on par with or surpassing 100B-parameter-class models, enabled by scalable agentic interaction environments for large-scale reinforcement learning.

0 engagement·1 source·arxiv
arXiv