Submitted by taesiri 11 GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents · 7 authors 1
Submitted by beanie00 7 Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? Microsoft Research 1 1
Submitted by jaewon040 4 4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video Seoul National University 1
Submitted by zx-Wu 4 When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning OPPO 5 2
Submitted by Seanie-lee 4 T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search KAIST AI 1 1
Submitted by Agcs12 2 CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare Mohamed Bin Zayed University of Artificial Intelligence 2 1
Submitted by YanAdjeNole 2 Can LLM Agents Be CFOs? A Benchmark for Resource Allocation in Dynamic Enterprise Environments The Fin AI 1
Submitted by Mercury7353 2 EVA: Efficient Reinforcement Learning for End-to-End Video Agent · 9 authors 1
Submitted by taesiri 1 UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience · 12 authors 1
Submitted by taesiri 1 Toward Physically Consistent Driving Video World Models under Challenging Trajectories · 13 authors 1
Submitted by taesiri 1 OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning · 14 authors 1
Submitted by taesiri 1 CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents · 8 authors 1
Submitted by garrying 1 UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Functionality Segmentation · 2 authors 2
Submitted by fromthesky 1 PLDR-LLMs Reason At Self-Organized Criticality Fromthesky Research Labs 0 1
taesiri 
