12 papers
Planning with the Views
Kangrui Wang, Linjie Li, Zhengyuan Yang +7
Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We call this capability view planning, requiring (1)understanding how a single action transf…
The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms
Jinghan Zhang, Zerui Cheng, Shiqi Chen +5
Traditional evaluations measure a learning algorithm's final performance on an i.i.d. test set, reducing learning to a single aggregate score. This approach obscures a fundamental…
RAGEN-2: Reasoning Collapse in Agentic RL
Zihan Wang, Chi Gui, Xing Jin +13
RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. Howeve…
SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
Shiqi Chen, Jingze Gai, Ruochen Zhou +13
Real-world tool-using agents operate over long-horizon workflows with recurring structure and diverse demands, where effective behavior requires not only invoking atomic tools but…
SkyLadder: Better and Faster Pretraining via Context Window Scheduling
Tongyao Zhu, Qian Liu, Haonan Wang +4
Recent advancements in LLM pretraining have featured ever-expanding context windows to process longer sequences. However, our pilot study reveals that models pretrained with shorte…
Internalizing World Models via Self-Play Finetuning for Agentic RL
Shiqi Chen, Tongyao Zhu, Zian Wang +7
Large Language Models (LLMs) as agents often struggle in out-of-distribution (OOD) scenarios. Real-world environments are complex and dynamic, governed by task-specific rules and s…