RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents Paper • 2609.22000 • Published 9 days ago • 77
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself Paper • 2609.22068 • Published 9 days ago • 132
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement Paper • 2609.14857 • Published 13 days ago • 214
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents Paper • 2609.17708 • Published 12 days ago • 73
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking Paper • 2609.13141 • Published 16 days ago • 65
FrontierChallenge: Evaluating Scientific Workflow Completion Paper • 2608.24979 • Published Aug 25 • 152
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models Paper • 2607.28609 • Published Jul 30 • 75
OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis Paper • 2604.15093 • Published Apr 16 • 30
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale Paper • 2603.25040 • Published Mar 26 • 132
TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents Paper • 2602.02196 • Published Feb 2 • 35