3 papers
cs.CV2026
SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning
Yong Xien Chng, Tao Hu, Wenwen Tong +10
While Vision-Language Models (VLMs) can solve complex tasks through agentic reasoning, their capabilities remain largely constrained to text-oriented chain-of-thought or isolated t…
cs.LG2025
DyMoDreamer: World Modeling with Dynamic Modulation
Boxuan Zhang, Runqing Wang, Wei Xiao +5
A critical bottleneck in deep reinforcement learning (DRL) is sample inefficiency, as training high-performance agents often demands extensive environmental interactions. Model-bas…
cs.AI2025
AWorld: Orchestrating the Training Recipe for Agentic AI
Chengyue Yu, Siyuan Lu, Chenyi Zhuang +14
The learning from practice paradigm is crucial for developing capable Agentic AI systems, yet it is severely hampered by inefficient experience generation, a bottleneck especially…