AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents Paper • 2605.17933 • Published May 18 • 7
SEAL: Synergistic Co-Evolution of Agents and Learning Environments Paper • 2605.24426 • Published May 23 • 9
Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Paper • 2608.11772 • Published Aug 12 • 3
Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents Paper • 2610.33568 • Published 12 days ago • 29
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence Paper • 2610.34283 • Published 11 days ago • 32
ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning Paper • 2610.18683 • Published 11 days ago • 16
PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking Paper • 2610.27628 • Published 16 days ago • 40
UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation Paper • 2610.09823 • Published 29 days ago • 33
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published Sep 10 • 223