most citedLearn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.SEShow all

1 paper · 1 filter

cs.SE2025

CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent

Haojia Lin, Xiaoyu Tan, Yulei Qin +9

Computer-using agents (CUAs) enable task completion through natural interaction with operating systems and software interfaces. While script-based verifiers are widely adopted for…