Iteris: Agentic Research Loops for Computational Mathematics
Iteris is an agentic AI research system designed to tackle open problems in computational mathematics, combining numerical experimentation, adversarial construction, and algorithm design within an automated loop. Applied to two open problems from a Simons Workshop collection, Iteris produced numerical evidence, constructions, and proof drafts that—after expert review—yielded verified results: a phase diagram comparing conjugate gradient vs. randomized coordinate descent, and a counterexample to QR factorization with column pivoting under low coherence. The paper argues that agentic AI can meaningfully participate in mathematical research workflows while human validation remains essential.
Related guides (3)
Related events (8)
Google's Aletheia agent uses Gemini 3 Deep Think to generate novel solutions to unsolved Erdős problems
Google researchers introduced Aletheia, an agentic workflow using Gemini 3 Deep Think that generates, verifies, and revises solutions to previously unsolved mathematical problems. Applied to Erdős problems, Aletheia produced 13 correct solutions out of 200 evaluated, with 4 being genuinely novel contributions not found in existing literature. The announcement also reveals Gemini 3 Deep Think's benchmark performance: 48.4% on HLE, 84.6% on ARC-AGI-2, and 93.8% on GPQA Diamond. The system demonstrates both the promise and current limitations of AI-assisted mathematical research, with a 6.5% correct-under-intended-interpretation rate on a hard problem set.
Accelerating discovery with the AI for Math Initiative
Google DeepMind has announced the AI for Math Initiative, a collaborative effort bringing together leading research institutions to advance the use of AI in mathematical research. The initiative aims to pioneer AI-driven approaches to mathematical discovery. The announcement comes from a Tier 1 source but the body text is sparse, providing limited technical detail about specific methods, models, or partner institutions involved.
VeriTrace: Cognitive-Graph Framework with Explicit Regulatory Loops for Deep Research Agents
VeriTrace introduces a cognitive-graph framework for deep research agents that replaces implicit LLM reasoning over intermediate representations with three explicit regulatory loops: interpretive update, deviation feedback, and schema revision. The system addresses contamination and error propagation in evolving mental models during complex multi-step research tasks. Using Qwen3.5-27B backbones, VeriTrace improves over the strongest matched baseline by 4.22 pp on DeepResearch Bench Insight and 5.9 pp Overall win rate on DeepConsult. With Config-DeepSeek, it achieves the strongest reproducible open-source result on DeepResearch Bench.
Can AI automate computational reproducibility?
This commentary introduces a new benchmark aimed at measuring AI's ability to automate computational reproducibility in scientific research. The piece examines whether AI systems can reliably re-execute and validate scientific computations, a key bottleneck in research integrity. It frames reproducibility automation as a concrete, measurable capability for evaluating AI's impact on science.
Latent Space profiles Axiom Math on verified generation and compounding intelligence
Latent Space interviews Carina Hong of Axiom Math, a company focused on formal verification applied to AI-generated mathematics. The discussion centers on 'verified generation' and 'compounding intelligence' as frameworks for scaling AI reasoning beyond informal, unverified outputs. The piece is relevant to the growing intersection of formal methods, mathematical reasoning, and AI capability development.
Data Points: Thinking Machines Interaction Model, ERNIE 5.1, Co-Mathematician, RL Conductor, and More
This edition of The Batch covers five notable AI developments: Thinking Machines' research preview of an 'interaction model' with a 200ms micro-turn multimodal architecture; Baidu's ERNIE 5.1, a compressed derivative of ERNIE 5.0 using only 6% of typical pre-training compute; Google DeepMind's Co-Mathematician collaborative workbench reaching 48% on FrontierMath Tier 4; a 7B RL Conductor model that orchestrates multi-agent workflows via reinforcement learning; and Google's Magic Pointer cursor system powered by Gemini. Secondary items include GitHub Copilot pricing restructuring ahead of usage-based billing.
Informath: Symbolic informalization for converting formal proofs to fluent natural language
The paper introduces Informath, a project for symbolic informalization — converting formally verified mathematics into readable natural language without loss of precision. The architecture uses Dedukti as an interlingua hub connecting proof systems (Agda, Lean, Rocq) and Grammatical Framework (GF) for multilingual natural language generation. The work is relevant to AI-assisted formal verification pipelines where autoformalization produces machine-checked proofs that need to be made human-interpretable.
Import AI 455: AI systems are about to start building themselves
Import AI issue 455 covers the emerging trend of AI systems automating AI research, framing it as a first step toward recursive self-improvement. The commentary synthesizes recent developments suggesting AI is beginning to participate meaningfully in its own development pipeline. As a tier-2 newsletter, this represents curated analysis of frontier AI research directions rather than primary reporting.