Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement Learning
Hongliang Wei, Xiaobing Tu, Yinggui Wang +6
Language-model agents are increasingly deployed through diverse harnesses that differ in system prompts, tool schemas, control loops, and trajectory formats. The same model can per…
cs.LG2025
TGPO: Tree-Guided Preference Optimization for Robust Web Agent Reinforcement Learning
Ziyuan Chen, Zhenghui Zhao, Zhangye Han +7
With the rapid advancement of large language models and vision-language models, employing large models as Web Agents has become essential for automated web interaction. However, tr…