Berkeley-affiliated StarTrail open-sources a deep research benchmark and paper-search toolkit
CShorten30 · x · 2026-11-04
StarTrail, affiliated with UC Berkeley EECS (Berkeley NLP / SkyLab), open-sourced a clean deep research benchmark plus a toolkit for searching its paper collection or building a visual index over your own corpus. The org also maintains LEANN (MLSys 2026 Best Paper; 97% storage savings for private on-device RAG, 13.8k stars), PixelRAG (pixel-native search replacing web parsing, 10.8k stars), and DRPixel (VLM-based page-native deep research benchmark, eval harness and training code).
More from coding & agent
- Karpathy's viral take: engineers' biggest regret is unsaved AI conversations — bfrench · 2026-11-04
- Apple lets apps bundle Siri skill files, devs mock the sloppy docs — msg · 2026-11-04
- YC-backed Simantic adds a simulation layer so AI agents can test firmware at software speed — ycombinator · 2026-11-04
- Bittensor Subnet 33 Launches Skill Store: Tested Skills Aim to Make Open Models Do Frontier Work — markjeffrey · 2026-11-04
- Building a 24-hour AI newsroom on Microsoft Copilot Harness: workflow beats prompts — WirelessLife · 2026-11-04
- Polyphonic to give AI agents their own Mac via open-source terminal-mac — RileyRalmuto · 2026-11-04