Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents Paper β’ 2604.06132 β’ Published 8 days ago β’ 114
MARS: Modular Agent with Reflective Search for Automated AI Research Paper β’ 2602.02660 β’ Published Feb 2 β’ 66
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning Paper β’ 2602.01058 β’ Published Feb 1 β’ 43
PaperBanana: Automating Academic Illustration for AI Scientists Paper β’ 2601.23265 β’ Published Jan 30 β’ 223
T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation Paper β’ 2512.21094 β’ Published Dec 24, 2025 β’ 25
CoDA: Agentic Systems for Collaborative Data Visualization Paper β’ 2510.03194 β’ Published Oct 3, 2025 β’ 30
MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining Paper β’ 2505.07608 β’ Published May 12, 2025 β’ 83