The Verification Horizon: No Silver Bullet for Coding Agent Rewards Paper • 2606.26300 • Published 7 days ago • 46
SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction Paper • 2605.20110 • Published May 19 • 4
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics Paper • 2606.10479 • Published 22 days ago • 19
SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents Paper • 2606.05761 • Published 27 days ago • 19
Draft-OPD: On-Policy Distillation for Speculative Draft Models Paper • 2605.29343 • Published May 28 • 36
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows Paper • 2605.14678 • Published May 19 • 108
Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning Paper • 2605.06326 • Published May 7 • 26
P1: Mastering Physics Olympiads with Reinforcement Learning Paper • 2511.13612 • Published Nov 17, 2025 • 135
P1: Mastering Physics Olympiads with Reinforcement Learning Paper • 2511.13612 • Published Nov 17, 2025 • 135
P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads Paper • 2602.09443 • Published Feb 10 • 59
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling Paper • 2605.13301 • Published May 13 • 165
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling Paper • 2605.13301 • Published May 13 • 165
TEMPO: Scaling Test-time Training for Large Reasoning Models Paper • 2604.19295 • Published Apr 21 • 35
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning Paper • 2602.11748 • Published Feb 12 • 38