ReTool: Reinforcement Learning for Strategic Tool Use in LLMs Paper • 2504.11536 • Published 8 days ago • 56
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories Paper • 2504.08942 • Published 12 days ago • 27
Awesome Computer Use Agents Collection https://github.com/ranpox/awesome-computer-use • 25 items • Updated Dec 18, 2024 • 12
AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials Paper • 2412.09605 • Published Dec 12, 2024 • 30
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction Paper • 2412.04454 • Published Dec 5, 2024 • 66