What if standard Reinforcement Learning isn't actually training your models to find the most likely correct answers? Researchers from CMU, Tsinghua, Zhejiang, and UC Berkeley introduce MaxRL to fix this fundamental limitation. MaxRL is a new framework that bridges the gap
MACHINE LEARNING
-
DeepThink Achieves IMO Gold Using Inference-Time Scaling
By
–
DeepThink is exceptionally good when powered by an inference-time scaling law that we showed in our Aletheia paper https://
arxiv.org/abs/2602.10177! These were benchmarked on our IMO-ProofBench graded by experts, which was the north-star metric leading to our IMO-gold achievement. Amazing -
Ray Kurzweil Birthday: Pioneer in Speech Recognition and Singularity
By
–
Happy birthday to Ray Kurzweil '70, an innovator in speech & text recognition. He's also a leading proponent of “the singularity.” Photo v/The Academy of Achievement
-
Aletheia: AI Math Research Agent Solves Erdős Open Problems
By
–
Yesterday we just shared Aletheia, our math research agent that enables autonomous math research and solving Erdos open problems. Yes, this Gemini 3 deep think was *the* deep think. It's launched! nitter.net/YiTayML/status/2021750… Yi Tay (@YiTayML) Introducing Aletheia, a math research agent powered by an advanced version of Gemini Deep Think that produces publishable math research (two papers, one completely automatic and another with human-AI collaboration) and solved multiple open Erdős problems. 😀🔥 Paper link below! 👇 — https://nitter.net/YiTayML/status/2021750645666328779#m
-
Gemini 3 Deep Think: New AI Model with Gold-Standard Performance
By
–
Gemini 3 Deep Think is here! 😎 This model is not only super strong in math and coding (IMO gold and 3455 codeforces ELO), it is also gold standard in physics and chemistry olympiads. 😃 Also sets new records on ARC-AGI-2 and HLE. Proud to be a (core) member of the Deep Think team. 🦾😆. Feeling the AGI!
-
DeepThink Achieves Gold-Standard Performance Across Math Physics Chemistry
By
–
In Jul 2025, even though our internal model achieved a gold-medal standard at IMO for maths, we could only ship a bronze-level one. 6 months in, the public can now have access to Olympiad gold-level #DeepThink not only in maths, but also theory physics and chemistry!
-
Google DeepMind Launches DeepThink V2 Reasoning Model
By
–
Congrats to the whole Deep Think team from @GoogleDeepMind for this amazing milestone of #DeepThink V2 launch! Such a great a model that powers so many state-of-the-art results from reasoning (ARC-AGI2) to deep knowledge (Humanity's Last Exam), multimodality (MMMU-Pro), coding
-
Deep Think Helping Researchers Catch Mathematics Research Errors
By
–
Fun to see Deep Think’s real-world impact. Check out how it’s helping researchers catch errors in high-level mathematics research papers. As "just" a math undergrad, I couldn't even dream to do any of this myself! pic.twitter.com/ueFGoOwPiX
— Oriol Vinyals (@OriolVinyalsML) 12 février 2026Fun to see Deep Think’s real-world impact. Check out how it’s helping researchers catch errors in high-level mathematics research papers. As "just" a math undergrad, I couldn't even dream to do any of this myself!
→ View original post on X — @oriolvinyalsml, 2026-02-12 16:20 UTC
-
Deep Think Benchmarks Push Frontiers of AI Intelligence
By
–
To better understand how Deep Think is pushing the frontiers of intelligence, take a look at these benchmarks across some of the most rigorous challenges in academia.
-
MLA Uses DSA Underneath According to DeepSeek V3.2
By
–
I'd say it the other way around: MLA uses DSA underneath, but that's right! E.g., from the DeepSeek V3.2 paper: