Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning
Kai Liu, Peijie Dong, Xinchen Xie +5
The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with cont…
cs.AI2025
RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy
Zhonghan Zhao, Wenwei Zhang, Haian Huang +4
Reasoning before action and imagining potential outcomes (i.e., world models) are essential for embodied agents operating in complex open-world environments. Yet, prior work either…