FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization Paper • 2603.19835 • Published 25 days ago • 335
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? Paper • 2603.24472 • Published 20 days ago • 53
Grounding World Simulation Models in a Real-World Metropolis Paper • 2603.15583 • Published 29 days ago • 153
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs Paper • 2603.09906 • Published Mar 10 • 75
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse Paper • 2603.12201 • Published Mar 12 • 53
Does Your Reasoning Model Implicitly Know When to Stop Thinking? Paper • 2602.08354 • Published Feb 9 • 263
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Paper • 2602.08222 • Published Feb 9 • 290