Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening Paper • 2609.18708 • Published 10 days ago • 80
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction Paper • 2609.10715 • Published 17 days ago • 329
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning Paper • 2608.14277 • Published Aug 14 • 36
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics Paper • 2606.10479 • Published Jun 9 • 21
Draft-OPD: On-Policy Distillation for Speculative Draft Models Paper • 2605.29343 • Published May 28 • 34
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling Paper • 2605.13301 • Published May 13 • 166
Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning Paper • 2605.06326 • Published May 7 • 26
Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents Paper • 2605.10832 • Published May 11 • 22
TEMPO: Scaling Test-time Training for Large Reasoning Models Paper • 2604.19295 • Published Apr 21 • 37
GEMS: Agent-Native Multimodal Generation with Memory and Skills Paper • 2603.28088 • Published Mar 30 • 84
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning Paper • 2602.11748 • Published Feb 12 • 28
P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads Paper • 2602.09443 • Published Feb 10 • 59
Spotlight on Token Perception for Multimodal Reinforcement Learning Paper • 2510.09285 • Published Oct 10, 2025 • 37