MERIT-Rank is proposed, a framework that models complementary reasoning trajectories to improve reranking robustness and develops Progressive Rank Policy Optimization (PRPO), a progressive training framework that stabilizes reasoning trajectories while continually improving ranking quality through staged optimization o...
Li-Jun Liu, Zheng-Zong Chen, Wen-Yan Li et al.· 0 citations
This work proposes MATCH, a closed-loop framework for model-aware tool learning with curriculum scheduling and hierarchically gated rewards, and shows consistent improvements across four backbones from two model families.
Shihao Liu, Hao Yin, Li-Jun Liu et al.· 0 citations
DirsWorld turns cross-device collaborative operation into an executable, reproducible, and diagnostically useful evaluation problem for research on reliable cross-device agents, and evaluates five frontier LLM-agent systems on a fixed evaluation set.
Hua-Tao Li, Xinwei Geng, Yu-Heng Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.