conftrace_

action entropy

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

staged training (1) action chunking (1) llm agent (1) vision-language-action model (1) robotic manipulation (1) policy optimization (1) reinforcement learning (1)

Papers

Adaptive Action Chunking at Inference-time for Vision-Language-Action Models CVPR 2026 When Instinct Guides and Insight Grounds: Staged RL Training for LLM Agents AAAI 2026