Large language models (LLMs) have shown great potential as general-purpose user simulators for interactive systems. Prior studies have demonstrated that training on high-quality data can substantially improve model reasoning and downstream task performance. However, the upper bound of user simulation is still constrain...
Jiawei Chen, Ruo-Xi Xu, Boxi Cao et al.· 0 citations
Joint Policy and Prompt Optimization (P O) is introduced to mitigate advantage collapse by alternating continuous policy updates with discrete prompt evolution, providing a self-reinforcing framework that facilitates more effective LLM alignment.
Xinyu Lu, Kaiqi Zhang, Jing-Li Yang et al.· arXiv.org· 2 citations
DocOps is introduced, a deterministically verifiable evaluation framework underpinned by a hierarchical taxonomy that deconstructs document operations inspired by real-world practices into atomic dimensions and escalating workflow complexities that exposes the capability boundaries of agents in maintaining global docum...
Jiazhen Jiang, Boxi Cao, Lingyong Yan et al.· arXiv.org· 1 citation
Experimental results show that RUPA consistently outperforms existing UQ methods by providing more accurate uncertainty estimates, enabling earlier failure detection, and improving uncertainty-guided agent execution across diverse agent tasks.
Zheng Ma, Boxi Cao, Yaojie Lu et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
