AlphaGeometry: An Olympiad-level AI system for geometry
Trieu Trinh and Thang Luong · Google DeepMind
AlphaGeometry turns learned suggestions for added geometric constructions into formal, checkable proofs.
Open library
The library
The essential reading of generative AI and agents, open in a clean reading view, with Meow and Standard summaries when available. No account needed to read.
560 papers · 558 with a Meow summary · 333 posts
Key publications from Anthropic, OpenAI, Google DeepMind, Meta, DeepSeek, Qwen, Z.ai, Kimi and other labs, plus the most influential essays and blogs.
Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad
Thang Luong and Edward Lockhart · Google DeepMind
Gemini Deep Think reached gold-medal-level performance by producing rigorous proofs directly from natural-language problems, within the IMO’s 4.5-hour limit.
Gemini Deep Think: Redefining the Future of Scientific Research
Thang Luong and Vahab Mirrokni · Google DeepMind
Aletheia’s key move is to make a proposed proof pass through a verifier that can revise it, restart it, or admit it is unsolved.
Language Models Perform Reasoning via Chain of Thought
Google Research
A few worked examples can prompt a model to unpack multi-step problems, but the reported gains emerge only at sufficient scale—around 100B parameters.
QwQ-32B: Embracing the Power of Reinforcement Learning
Qwen Team · Qwen
Qwen reports that 32-billion-parameter QwQ-32B performs comparably to DeepSeek-R1 (671 billion parameters, 37 billion activated), arguing that reinforcement learning can help a strong pretrained model improve its performance.
Why We Think
Lilian Weng
More computation at inference can improve reasoning, but only when the extra work is spent well: longer traces and self-revision are not automatically more reliable.
Understanding Reasoning LLMs
Sebastian Raschka, PhD · Sebastian Raschka
Reasoning models are a specialization for multi-step problems—not a universal upgrade—and their gains come with compute, cost, and overthinking trade-offs.
The State of Reinforcement Learning for LLM Reasoning
Sebastian Raschka, PhD · Sebastian Raschka
The article argues that reasoning-focused reinforcement learning can improve hard-task performance beyond scaling alone—but reward design, response length, and evaluation quality determine whether the gains are useful.
DeepSeek R1's recipe to replicate o1 and the future of reasoning LMs
Nathan Lambert
R1 makes reasoning training more reproducible: the author argues its new behavior comes from large-scale reinforcement learning, not an explicit inference-time search procedure.
What comes next with reinforcement learning
Nathan Lambert
The author expects more frequent model updates from scaling current RL, but argues that this does not show models can learn from very long tasks or continually adapt from experience.
Asymmetry of verification and verifier’s rule
Jason Wei
The useful leverage is not just generating candidates; it is building a quick, trustworthy way to tell which ones work.
Magistral | Mistral AI
Mistral
Mistral presents Magistral as a reasoning model for traceable, multilingual work. Its benchmark and speed claims are useful signals, but the announcement gives limited evaluation detail.
Gemini 3 Deep Think: Advancing science, research and engineering
The Deep Think team · Google DeepMind
Google upgraded Gemini 3 Deep Think for difficult science, research and engineering work, pairing benchmark claims with early examples from research and engineering.
Some thoughts on the Navier–Stokes Millennium Prize Problem
Simon Willison
Willison argues that a rumor of an unpublished solution can trigger an expensive LLM race—and that the episode leaves the meaning of “used to improve model performance” unclear.
GPT-6 Astra, Looped Transformers, and Hidden Reasoning
Sebastian Raschka, PhD · Sebastian Raschka
Looped transformers reuse the same blocks for extra depth, but that still costs compute. Raschka finds no strong evidence that looping makes chain-of-thought deceptive, and Astra's rumored architecture is unconfirmed.
Controlling Reasoning Effort in LLMs
Sebastian Raschka, PhD · Sebastian Raschka
Reasoning effort is a trained control over how much inference-time work an LLM spends—not a magic prompt word—and it trades answer quality against tokens, cost, and latency.
Experts Have World Models. LLMs Have Word Models.
Ankit Maloo · Latent Space
The essay argues that expert work depends not just on producing polished output, but on anticipating how self-interested people will react, adapt, and exploit it.
Thinking to recall: How reasoning unlocks parametric knowledge in LLMs
Google Research
Reasoning can expose parametric memory—knowledge encoded in a model’s weights—even on simple fact questions, through extra computation and related-fact priming.