Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts Paper • 2601.03315 • Published 5 days ago • 5
WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks Paper • 2601.02439 • Published 6 days ago • 15
SOP: A Scalable Online Post-Training System for Vision-Language-Action Models Paper • 2601.03044 • Published 5 days ago • 26
NitroGen: An Open Foundation Model for Generalist Gaming Agents Paper • 2601.02427 • Published 7 days ago • 35
Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation Paper • 2601.00664 • Published 9 days ago • 50
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling Paper • 2512.23959 • Published 12 days ago • 96
Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding Paper • 2512.17220 • Published 23 days ago • 110
MAI-UI Technical Report: Real-World Centric Foundation GUI Agents Paper • 2512.22047 • Published 16 days ago • 26
TimeBill: Time-Budgeted Inference for Large Language Models Paper • 2512.21859 • Published 16 days ago • 24
QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management Paper • 2512.12967 • Published 27 days ago • 103