DeepMind's Aletheia agent on Gemini Deep Think was evaluated on 700 open Erdős problems and autonomously solved four.
DeepMind's Aletheia agent on Gemini Deep Think was evaluated on 700 open Erdős problems and autonomously solved four.
DeepMind built Aletheia, a math research agent on Gemini Deep Think, with three parts: a generator, a natural-language verifier and a reviser. The verifier flags flaws, and the agent either revises the solution or restarts. It can also admit failure. It uses Google Search and web browsing to check published literature. In a semi-autonomous evaluation it was run against 700 open problems from Bloom's Erdős database.
It autonomously solved four open Erdős questions: 652, 654, 1040 and 1051. Erdős-1051 also led to a generalization in a separate paper. The post claims no major-advance or breakthrough-level results.
The agent's ability to say it can't solve a problem saved researchers time. The prompts and outputs are on GitHub, and the full details are in the arXiv paper.
Here is an open math problem I want to work on: [problem statement]. Search the literature to check whether it is already solved, then try to build a proof or find a counterexample, showing each step. Finish with a clear verdict: solved, partial progress, or stuck, and list any steps that I should verify by hand.
Make pulls contracts from Gmail, Gemini extracts the term and notice period, and a Sheets register emails the owner 60, 30 and 7 days before each deadline.
A self-hosted n8n job reads your calendar, unread email and Notion tasks at 7am and sends one short brief of what matters today.
An n8n and Gemini agent receives patient chat messages, keeps context, uses clinic info from Google Sheets and responds to enquiries.