OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
Paper • 2606.29537 • Published • 24
Christopher Glaze
cmglaze
AI & ML interests
weak supervision, structured prediction, generative AI, probabilistic graphical models, NLP
Recent Activity
liked a dataset 4 days ago
snorkelai/ping-or-peek published a dataset 4 days ago
snorkelai/ping-or-peek updated a dataset 12 days ago
snorkelai/ping-or-peekOrganizations
upvoted a paper 4 months ago
upvoted 3
papers about 1 year ago
Automating Benchmark Design
Paper • 2510.25039 • Published • 16
AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
Paper • 2509.08755 • Published • 56
Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents
Paper • 2509.09265 • Published • 47