Long-horizon search requires agents to gather evidence across multiple steps and synthesize it into well-supported answers. The recent agent harnesses provide a natural and promising framework to support such long-running search processes. As interaction histories grow, one single agent in harnesses might get stuck and...
Shanyong Wang, Zhen-Wen Ji, Lei Jin et al.· 0 citations
Detailed image captioning requires accurate and comprehensive descriptions of fine-grained visual content, yet caption quality spans factual accuracy, information coverage, and clarity. Compared with conventional methods that rely mainly on high-quality supervision or holistic rewards, rubric-based reinforcement learni...
Zhen-Wen Ji, Lei Jin, Shanyong Wang et al.· 2 citations
The MemLens is presented, a value-aware memory management system that takes memory records as first-class data objects and can serve as an efficient, interpretable, and personalized long-term memory management system for agents.
Shuyue Wei, Chang Liu, Zi-Mu Zhou et al.· Proceedings of the VLDB Endo...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.