The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 3 days ago • 309
Player-1: Learning to Play from Synthetic Experience Paper • 2610.20584 • Published 15 days ago • 353
RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation Paper • 2609.16900 • Published Sep 15 • 49
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening Paper • 2609.18708 • Published Sep 16 • 85
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing Paper • 2609.08936 • Published Sep 8 • 155