---
id: "2026-02-11-deepmind-aletheia-deep-think-science"
url: "https://postcutoff.com/e/2026-02-11-deepmind-aletheia-deep-think-science/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2026-02-11"
date_precision: day
category: science
importance: 4
confidence: high
status: [Event confirmed, Awaiting review]
verification: Expert-checked
sources: 3
editor: human editor
human_review: null
version: "2026-10-19"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-02-11-deepmind-aletheia-deep-think-science/

# DeepMind's Aletheia agent and Gemini Deep Think report autonomous Erdős solutions and new physics and CS results

Google DeepMind described Aletheia, a Gemini Deep Think–based maths research agent. It autonomously solved Erdős problems #652, #654 and #1040 and resolved #1051, which led to a peer-reviewed generalisation. A semi-autonomous sweep of 700 open Erdős problems resolved 4 and found existing literature solutions for several more. With 18 external researchers, Deep Think also produced a cosmic-string gravitational-radiation result and refuted a decade-old online-optimisation conjecture.

## Key facts
- Aletheia paper: arXiv 2602.10177; up to 90% on IMO-ProofBench Advanced
- Autonomous: Erdős #652, #654, #1040; #1051 resolved and generalised
- 700-problem sweep: 4 open questions resolved; several 'open' problems found already solved in the literature
- Physics: a new Gegenbauer-polynomial solution removing singularities in cosmic-string gravitational radiation calculations
- One paper (eigenweights) classed by DeepMind as essentially autonomous and publishable

## What happened

DeepMind packaged Gemini Deep Think into an agent that generates, checks and revises proofs, and released a batch of results across maths, CS and physics.

## Why it matters

Google's answer to OpenAI's maths push showed that several labs could now produce publishable research-level results, although many were on problems nobody had seriously attacked.

## What is disputed or not yet verified

- Verification: Batch of results in unrefereed preprints (arXiv 2602.10177 and companion papers), checked by the collaborating mathematicians, who are co-authors; one generalisation reported as peer-reviewed (not verified here). Status varies by result

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Google DeepMind: Accelerating mathematical and scientific discovery with Gemini Deep Think](https://deepmind.google/blog/accelerating-mathematical-and-scientific-discovery-with-gemini-deep-think/) (deepmind.google, official)
2. [Aletheia paper (arXiv 2602.10177)](https://arxiv.org/abs/2602.10177) (arxiv.org, paper)
3. [InfoQ: DeepMind Aletheia agentic math](https://www.infoq.com/news/2026/04/deepmind-aletheia-agentic-math/) (infoq.com, press)

## Changes

- 2026-10-19: Status confirmed → pending (batch of unrefereed preprints checked by co-authors, not independently)
- 2026-09-29 (filed): Created

## Related

- 2026-02-14: [AI solves about half of 10 unpublished research problems in the 'First Proof' challenge](https://postcutoff.com/e/2026-02-14-first-proof-challenge/index.md)
- 2026-01-06: [Erdős problem #728 solved near-autonomously by GPT-5.2 Pro and Harmonic's Aristotle, with a Lean proof](https://postcutoff.com/e/2026-01-06-erdos-728-gpt-5-2-aristotle/index.md)