aiqbench analysis
Resolution, an AI safety startup, used a team of AI agents to autoformalize resolution of singularities in Lean, producing about 600k lines of code in roughly a week for an estimated $135,000 in token spend. The write-up is a useful concrete data point on how much agentic systems can accelerate formal mathematics, and the team's claim that the result could support research on loss landscape geometry and generalization is a hypothesis to watch, not an established finding. Readers should note that the reported costs and timelines come from a single company's account.
Import AI 478: Math for alignment; ProgramBench; and Mirendil shows what RSI means

Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe. Subscribe now How math could help alignment:…What the “industrialization of mathematics” means for safety…AI safety startup Resolution (formerly known as Sequent, Import AI 461) has published work on […]
Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe. How math could help alignment:…What the “industrialization of mathematics” means for safety…AI safety startup Resolution (formerly known as Sequent, Import AI 461) has published work on how it has automatically formalized some mathematical statements related to statistical learning theory. Specifically, the team has autoformalized the resolution of singularities, which they believe “lays the groundwork for further automated research into the relationship between loss landscape geometry and generalization.” How they did it: I’ll skip over the math and concentrate on how they did it, which gives us some broader lessons for how people are using AI systems to push on the frontier of knowledge. A Resolution researcher “started by working with agents to develop two plans: a high-level, human-interpretable version and a detailed (112-page) plan divided into atomic steps that closely followed the existing literature,” they write. The researcher “then deputized an orchestrator agent to carry out the plan, spinning up agents to do pen-and-paper math, write Lean, and handle support functions like checking that things were staying on track… the execution phase required…
Excerpt shown under the publisher's RSS terms · 200 words · full text and figures are on the publisher's site
Related coverage
Spine: Compiling Subtask Trees into Structured Context for Long-Horizon Coding Agents
arXiv · Oct 29, 2026

[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026

[AINews] Claude Opus 5.5, the new default model for AINews — and everybody cuts prices 40-50%
Latent Space · Sep 23, 2026

Top 10 Open-Source Benchmarks for AI Coding Agents in 2026
KDnuggets · Aug 20, 2026