You.com, NVIDIA and CoreWeave post-train search model, lifting BrowseComp accuracy 22.94%
_ScottCondron · x · 2026-10-27
You.com partnered with NVIDIA and CoreWeave to post-train NVIDIA Nemotron 3.5 Lightning (SFT + RL rollouts), with the thesis that better web search means training models to use search better: reason through queries, find the right information, and reach answers with fewer tool calls.
- BrowseComp accuracy rose from 36.97% to 45.45% (+22.94%)
- Average tool calls per task dropped from 168 to 115 (30% fewer)
- Done in a three-week sprint; full post-training details published
Related event: CoreWeave, NVIDIA Boost Search Agent in Three-Week RL Sprint(2 posts)→
More from coding & agent
- Cursor launches Agent SDK: agents as code with Markdown prompts and TypeScript tools — soleio · 2026-10-27
- Vibecheck, the 'usable formal methods' hackathon, sells out two floors in SF — spikedoanz · 2026-10-27
- How do you verify AI agent outputs beyond unit tests and LLM-as-judge? — Practical_Green5775 · 2026-10-27
- AI agents may soon become the only way to run code, not just write it — IgorCarron · 2026-10-27
- Hermes Agent used as browser QA tester finds 8 issues in a bug-seeded site — techlatest_net · 2026-10-27
- Open-source FableCut lets AI agents edit a real video timeline via remote MCP — FastPresence9799 · 2026-10-27