AREX: Towards a Recursively Self-Improving Agent for Deep Research Paper • 2607.21461 • Published 27 days ago • 154
AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery Paper • 2604.25256 • Published Apr 28 • 30
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters Paper • 2602.10604 • Published Feb 11 • 201
Running MCP 196 Recommend Similar Papers 🌖 196 Generate similar paper recommendations from a Hugging Face link
EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling Paper • 2509.23909 • Published Sep 28, 2025 • 34 • 11