1 citations · 1 across the 2 of their papers we have counts for
3 papers
cs.CL2026
ClawGym II: Exploring Black-Box RL on Agent Harness
Huatong Song, Fei Bai, Ming Yang +17
Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning through compl…
cs.CL2026
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents
Jia Deng, Yimeng Chen, Xiaoqing Xiang +9
Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. Existing synthesis methods of…
cs.LG2025★ 1 cited
HGTUL: A Hypergraph-based Model For Trajectory User Linking
Fengjie Chang, Xinning Zhu, Zheng Hu +1
Trajectory User Linking (TUL), which links anonymous trajectories with users who generate them, plays a crucial role in modeling human mobility. Despite significant advancements in…