OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks Paper • 2606.29537 • Published 13 days ago • 22
AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning Paper • 2509.08755 • Published Sep 10, 2025 • 56
Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents Paper • 2509.09265 • Published Sep 11, 2025 • 47