A guided tour of how AI systems are being built, trained and tested to make genuine discoveries, from open-ended search and idea generation to autonomous research agents and benchmarks built on unsolved problems.


A scientist works at a stereo microscope with a fine probe, vintage colour · Photo: National Cancer Institute
In a 2026 preprint, Large Discovery Models pair LLM suggestions with a statistical model that weighs predicted value against uncertainty to decide what earns a costly test.
arXiv preprint · 16 August 2026

Photo: National Cancer Institute
A 2026 preprint fine-tunes small open models on the score-improving steps of AI-driven evolutionary searches, with average gains on test problems that are uneven and unreplicated.
arXiv preprint · 27 June 2026

Photo: Fulvio Ciccolo
A 2026 preprint adds an evolving web-search loop to AI-driven evolutionary search, with large gains for one model, modest ones for another and losses for a third.
arXiv preprint · 30 September 2026