Tag
Introduces Octopus, a neuro-symbolic architecture that combines LLM swarms with algorithmic physics engines for autonomous discovery of cancer vulnerabilities, identifying IGF2 as a biomarker for drug resistance.
A paper published in Science Magazine demonstrates a broad range of life science research being conducted autonomously using agentic AI to accelerate discovery.
The paper introduces Sealed Joint Search (SJS) and the Agora system, where five specialized LLM agent classes collaborate to evolve alpha factors. On a 91-day CSI 1000 holdout, Agora achieves a portfolio Sharpe of +1.87, significantly outperforming baselines, and the discovered metrics appear as emergent properties of the system.
OpenAI and Molecule.one collaborated to have their AI systems (GPT-5.4 and Maria) autonomously select research areas, generate proposals, and run experiments in organic chemistry, achieving yield improvements for 88% of tested reactions — a first for AI-driven open-ended scientific discovery.
This paper introduces Cartograph, a verification layer for AI scientists that couples subspace experiment steering, ambiguity resolution, and library inadequacy detection. The framework outperforms baselines in autonomous discovery testbeds and retrospectively flags inconclusive claims in the A-Lab materials system.
This paper introduces GRAFT-ATHENA, a self-improving agentic framework that autonomously discovers and evolves numerical algorithms for scientific problems. It demonstrates near-machine-precision accuracy on physics-informed machine learning benchmarks and successfully tackles complex engineering challenges.
An OpenAI model has autonomously solved the planar unit distance problem, a famous open question in mathematics posed by Paul Erdős in 1946, by discovering a new family of constructions that outperform square grids. This marks the first time AI has autonomously proven a prominent open problem in mathematics.