ASI‑Bench is a new benchmark that evaluates AI systems on their ability to conduct innovative exploration and autonomous scientific research across 11 domains, using 60 project‑level tasks. It progressively removes human methodological guidance to test whether AI can independently select methods, execute research, and produce verifiable results. Results from 18 state‑of‑the‑art agent–model configurations show a sharp performance drop when guidance is reduced, indicating current systems still rely heavily on human input.
By Junwei Zhou, Zhen Sun, Binyu Li, Jiangyu Zhou, Yuexi Pan, Hengyu Wang, Honghe Ren, Xiaohan Jia, Xueyang Zhou, Xiaoyu Cao, Yongchao Chen, Yuanning Feng, Junhao Wu, Cheng Zhang, Sijia Chen, Haoyu Xue, Chengsong You, Huan Wang, Koutian Wu, Peigan Gao, Jiakun Wu, Wenzhe Li, Ergan Shang, Qingyuan Zheng, Jingjing Zhou, Ruixuan Jia, Yan Xu, Hongrui Zhang, Xiao-Han Ma, Zhengxiang Cheng, Yuexing Hao, Liting Mai, Xianglin Ji, Wenjun Zhang, Zhuofan Chen, Yixiao Huang, Chi Wang, Wenyue Hua, Yilun Hao, Yuantao Zhai, Ziyan Zhao, Jingyan Xie
arXiv:2602. 16793v2 Announce Type: replace Abstract: In the past year, custom and unreleased math reasoning models reached gold medal performance on the International Mathematical Olympiad (IMO).
By Xingyu Dang, Rohit Agarwal, Rodrigo Porto, Anirudh Goyal, Liam H Fowl, Sanjeev Arora
arXiv:2610.17090v1 Announce Type: cross
Abstract: On 6 October 2026 OpenAI published an initial 722 AI-written mathematical manuscripts, organized into 372 problem families, in the public repository...
By Ying Xie
arXiv:2608. 15979v1 Announce Type: new Abstract: Large language models produce outputs presented as discoveries - new proofs, conjectures, or molecules.
By Eric Xie, Wenqian Ye, Aidong Zhang
The paper introduces the AI Mathematician (AIM) framework, which leverages Large Reasoning Models (LRMs) to tackle frontier mathematical research. AIM addresses the complexity and procedural rigor of research problems through an exploration mechanism for longer solution paths and a pessimistic reasonable verification method for reliability. Early experiments show AIM can autonomously construct significant proof components and uncover non‑trivial insights across real‑world mathematical topics.
By Yuanhang Liu, Yanxing Huang, Yanqiao Wang, Peng Li, Yang Liu
The paper introduces HorizonMath, a benchmark of 113 largely unsolved mathematical problems across eight domains, paired with an open-source framework for automated verification. It focuses on the generator‑verifier gap, targeting problems that are hard to discover but easy to verify computationally, thereby avoiding costly formal proof verification or manual review. Using this framework, the authors found six novel solutions—three each from GPT‑5.4 Pro and GPT‑5.6 Sol—demonstrating that current models can contribute to mathematical research, while most state‑of‑the‑art models score below 10%.
By Erik Y. Wang, Sumeet R. Motwani, James V. Roggeveen, Eliot Hodges, Dulhan Jayalath, Charles London, Kalyan Ramakrishnan, Jakob Foerster, Cheng Zhang, Flaviu Cipcigan, Philip Torr, Alessandro Abate
arXiv:2606. 30481v1 Announce Type: cross Abstract: Current large language models are extraordinary statistical engines.
By Ziqin Yuan, Jaymari Chua
arXiv:2607. 13899v1 Announce Type: new Abstract: We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models based on the models' internal mechanisms.
By Michal \v{S}tef\'anik, Philipp Mondorf, Andreas Waldis, Qianying Liu, Chuan Yang, Michal Spiegel, Josef Kucha\v{r}, Marek Kadl\v{c}\'ik, Adam Vawda-Oomerjee, Chaoran Liu, Simon Frieder, Barbara Plank, Fazl Barez, Pontus Stenetorp
The paper introduces GAP, a methodology that automatically generates mathematically equivalent variants of existing math problems using surface renames and kernel rewrites. Applying GAP to all 1,051 William Lowell Putnam Competition problems creates PutnamGAP, a 6,306-item dataset with 5,255 unseen variants. Evaluation of 18 commercial and open-source LLMs shows accuracy drops across all models, especially under kernel rewrites, indicating a persistent weakness in transferring proof plans to new mathematical settings.
By Yuren Hao, Xiang Wan, ChengXiang Zhai
EPOCH is an evidence‑governed architecture for AI research agents that improves how candidate discoveries are evaluated and validated. By combining explicit task contracts, typed memory, active falsification, admission checks, and independent replay, EPOCH ensures that each candidate is judged against the strength and scope of its claim. The system achieves state‑of‑the‑art performance on several benchmarks, including AlgoTune, Math14, and AgentHPO, and demonstrates significant advances in executable constructions, algorithm optimization, counterexamples, and proof‑supported results across ten discovery problems.
By Binjie Guo, Aisheng Mo, Ruitong Li, Xinle Deng
The paper reports on the Ramanujan Challenge, a benchmark of research‑level number theory problems, and evaluates submissions from AI models, CAS, and formal tools. It highlights that some correct solutions differ conceptually from official ones and even proves a published open conjecture. The authors introduce an AI‑assisted evaluation pipeline that significantly lowers false positives in natural language proofs and improves accuracy for supporting code, offering a scalable method for assessing high‑level mathematical work.
By Alan Sorani, Ashvni Narayanan, Michael Shalyt, Tali Monderer, Rotem Kalisch, Hila Barkan, Elyasheev Leibtag, Shachar Weinbaum, Carsten Schneider, John Campbell, Ido Kaminer
arXiv:2608. 06933v1 Announce Type: cross Abstract: Today, we improve models by training and evaluating them on problems at the frontier of their abilities.
By Sarah Pratt, Jae Sung Park, Scott Geng, Ali Farhadi