news
| Feb 08, 2026 | New preprint: ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development is now available on arXiv! |
|---|---|
| Feb 08, 2026 | Our paper ProjDevBench was featured on 量子位 (QbitAI), a leading Chinese tech media outlet! |
| Jul 21, 2025 | New preprint: ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry is now available on arXiv! |