Sage S2.1 Flash Technical Reportwith Kun Cai, Haodong Chen, Guangran Cheng, Qingxiu Cheng +2011 versionW_3gpqw6fyv1 · current
AgentV-RL: Scaling Reward Modeling with Agentic VerifierJiazheng Zhang, Ziche Fu, Zhiheng Xi et al.0 citations2604.16004v12026arXiv
TaxoBench: Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert TaxonomiesMing Zhang, Jiabao Zhuang, Wenqing Jing et al.0 citations2601.12369v62026arXiv
OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty AssessmentMing Zhang, Kexin Tan, Yueyuan Huang et al.1 citation2601.01576v22026arXiv
Two Minds Better Than One: Collaborative Reward Modeling for LLM AlignmentJiazheng Zhang, Wenqing Jing, Zizhuo Zhang et al.0 citations2505.10597v32025arXiv