TuringSpace: Grounding Spatial Intelligence in Action with Interactive CAPTCHAs Paper • 2611.25387 • Published 2 days ago • 23
AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics Paper • 2610.28589 • Published Oct 20 • 24
CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow? Paper • 2610.25078 • Published Oct 18 • 46
Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds Paper • 2610.27999 • Published Oct 20 • 97
view article Article The Most Intuitive Way to Understand Score Function Centering: Understand Trainer-Generator Mismatch in Async RL from the Score Function NormalUhr • Oct 15 • 18
Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL Paper • 2610.21439 • Published Oct 15 • 29
SanSi: A Looped Typed Decision Model for System 1.5 Thinking Paper • 2610.07730 • Published Oct 6 • 18
CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning Paper • 2609.36820 • Published Sep 29 • 19
A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review Paper • 2609.39027 • Published Sep 30 • 15
Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL Paper • 2610.00574 • Published Sep 30 • 31
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents Paper • 2605.25624 • Published May 25 • 34
T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning Paper • 2605.02178 • Published May 4 • 10
Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL Paper • 2604.17073 • Published Apr 18 • 9
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention Paper • 2506.13585 • Published Jun 16, 2025 • 275
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents Paper • 2604.10577 • Published Apr 12 • 27