The second paper "Accelerating Scientific Research with Gemini: Case Studies and Common Techniques" builds on similar agentic reasoning ideas, and identifies effective "recipes" for collaboration, specifically the "Advisor" model, where humans guide AI through iterative
@lmthang
-
Human-AI Interaction Card Proposes Novel Transparency Framework
By
–
Inspired by the "model" card, we also propose a novel concept of Human-AI Interaction (HAI) card to better capture how the experts and AI interacted. The goal here is for transparency to the general public. This is only the first proposal and we hope the community can further
-
AI Generates First Research Papers Without Human Intervention
By
–
At research-level mathematics, we are excited to announce the first wave of 6 research papers:
* Reliable autonomous research. A research paper (Feng26, https://
arxiv.org/abs/2601.23245) generated by AI without any human intervention, which calculates certain structure constants in -
Aletheia: Advanced AI Reasoning with Deep Think and Scaling
By
–
The three main sources that power Aletheia are:
#1: an advanced version of Gemini Deep Think for tackling extremely hard reasoning problems
#2: a novel inference-time scaling law that extends from
Olympiad-level problems to PhD-level exercises
#3: intensive tool use such as -
Foundation Models Struggle with Advanced Mathematics Research
By
–
Research-level mathematics draws on advanced techniques from vast literature, with papers often spanning dozens of pages. While foundation models possess a large knowledge base from pretraining, their understanding of advanced subjects remains superficial due to data scarcity,
-
Gemini Deep Think Accelerates Mathematical Scientific Discovery
By
–
Here's the link to the joint blog post: https://
deepmind.google/blog/accelerat
ing-mathematical-and-scientific-discovery-with-gemini-deep-think/
…. See details of the two papers below! -
AI Accelerates Knowledge Discovery in Mathematics and Physics
By
–
6 months in, after the IMO-gold achievement, I’m very excited to share another important milestone: AI can help accelerate knowledge discovery in mathematics, physics, and computer science! We’re sharing Two new papers from @GoogleDeepMind and @GoogleResearch that explore how
-
AI Collaborative Research on Erdős Problems with Comic Documentation
By
–
Another cute comic for this work: a nice collaborative story between #Aletheia and human experts for cracking Erdős problems, thanks @AwaitSeedIgnite! I wish we have ComicBanana for all papers 🙂 First four pages here and full one in this link https://
drive.google.com/file/d/1XecW9W
tDDNl-XE5-lm9DB71KX0FcDMH5/view?usp=sharing
…. -
Erdős Problem 1051 Solved Using Gemini Deep Think
By
–
Most notably is the Erdős 1051 problem in which our collaborators were able to derive a generalized version of it by interacting with Gemini Deep Think. See the cute comic below if you haven't!
-
Aletheia AI Cracks 13 Erdős Problems With Novel Solutions
By
–
Here's the full list of 13 #Erdős problems cracked by #Aletheia and ranked by impacts from truly novel solutions to simply literature identification. * marks problems that others have concurrently reported while we were preparing this manuscript.