CocoaBench: Evaluating Unified Digital Agents in the Wild Paper • 2604.11201 • Published 4 days ago • 32
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 30 days ago • 94
Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents Paper • 2509.23040 • Published Sep 27, 2025 • 12
AIonopedia: an LLM agent orchestrating multimodal learning for ionic liquid discovery Paper • 2511.11257 • Published Nov 14, 2025 • 25
LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts Paper • 2510.19363 • Published Oct 22, 2025 • 63