Multi-agent AI lab autonomously researches quantum spins in diamond, revises drifting experiments
krishnan · x · 2026-10-31
An October 29 preprint from Institute of Science Tokyo presents an autonomous research lab of LLM-based agents that review each other's work and can stop or redirect investigations.
- Studying ensembles of quantum spins in diamond, the agents derived the minimum calibration settings needed to predict responses to a family of microwave pulse sequences
- They ran computational checks and designed experiments to distinguish competing predictions
- When repeated reference measurements showed signal drift, the agents judged the result inconclusive and revised the protocol without relaxing acceptance criteria; the revised experiment met them and supported theory (arXiv 2610.40589)
More from coding & agent
- ASC CLI now covers Xcode commands, fastlane migration, and Linux builds via xtool — rudrank · 2026-10-31
- LangChain founder: agent observability is 'Databricks for agents', not Datadog — hwchase17 · 2026-10-31
- A 710k-line PR ports pi-durable and Chord to Rust for crash-safe agent runs — jasonkneen · 2026-10-31
- Strix Halo one-command Docker for vLLM: Qwen3.8-Flash-Next hits 43 tok/s decode — asfbrz96 · 2026-10-31
- Anthropic's VS Code extension on Cursor backdoored for nearly 12 hours, up to 5,000 devs exposed — Ars Technica AI · 2026-10-31
- dhh on coding in the AI era: code is no longer the bottleneck, humans are — NERDDISCO · 2026-10-31