Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published 6 days ago • 50
MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations Paper • 2607.28956 • Published 10 days ago • 95
Poplar: A Scalable Pipeline for Human-Centric Image Dataset Synthesis Paper • 2608.00440 • Published 9 days ago • 10
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement Paper • 2607.23802 • Published 15 days ago • 103