Locus: agents should adapt the discovery loop itself, not just orchestrate tools
yusufroohani · x · 2026-11-04
Most agents in science are deployed to boost throughput by orchestrating tools. The Locus team is instead building systems that autonomously adapt the discovery loop itself — tackling noisy evaluations, costly experiments, and staying on task over long horizons.
Related event: Intology Unveils Locus, an Autonomous Scientific Discovery System(12 posts)→
More from coding & agent
- Berkeley-affiliated StarTrail open-sources a deep research benchmark and paper-search toolkit — CShorten30 · 2026-11-04
- Baseten launches Grid, Sandboxes and Loops in one week to unify inference and training — baseten · 2026-11-04
- AI job-search framework built on Claude Code hits 69.3k GitHub stars — adnan_hashmi · 2026-11-04
- DuplexAgent-RSI separates live speech from async agent work in voice assistants — jiqizhixin · 2026-11-04
- Team shares meticulous agent-driven workflow for landing open-source PRs in Turso — glcst · 2026-11-04
- Aohan: inference should be fast enough that the environment becomes the bottleneck — _arohan_ · 2026-11-04