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
ReuF2F is a Lean 4 benchmark comprising 244 formalized open problems sourced from Research Experiences for Undergraduates (REU). It aims to evaluate coding agents on less prominent, entry‑level research problems across diverse mathematical subfields, using a Docker‑based Lean project setup and a unified harness called Leanimum‑agent. The study finds that even the best model solves only about 40 % of the problems, indicating significant room for improvement.
By Zeyu Zheng, Yiyang Liu, Yuyang Zhao, Congmin Zheng, Jiachen Zhu, Jianian Chen, Kangning Zhang, Kayue Daniel Wong, Lingyu Yang, Rong Shan, Shihao Chen, Thomas Zhu, Wentao Zhang, Xiaopeng Li, Yan Hu, Yongxi Lin, Yuxiang Chen, Zhuoying Ou, Jianghao Lin, Jeremy Avigad, Prasad Tetali, Jingbang Chen, Sean Welleck
arXiv:2610.09769v1 Announce Type: cross
Abstract: Large language models are increasingly contributing to mathematical research, where progress often depends on efficient proof search, incremental imp...
By Adri\'an Z\'ame\v{c}n\'ik, Mat\v{e}j Kripner, Martin Kouteck\'y, Martin Balko, Jan Greb\'ik, Pavel Hub\'a\v{c}ek, Robert \v{S}\'amal, V\'aclav Rozho\v{n}
The paper presents a system that transforms open‑problem listings in research fields into a structured, queryable knowledge graph. It combines a hand‑curated problem layer with an evidence layer derived from bibliographic data, linked through typed, provenance‑carrying connections. The authors evaluate the approach on database and AI problem catalogs, showing that the new graph can answer all previously answerable queries and additional ones about recent work, but also reveal limitations in automated status judgments, leading to a design recommendation that status changes must be proposed with evidence and reviewed by humans.
By Madhulatha Mandarapu, Sandeep Kunkunuru
Bolzano is a multi‑agent, open‑source system that employs parallel prover agents and a verifier agent to conduct proof search while maintaining a human‑readable research state. In initial manual trials on expert‑selected problems, it produced eight proofs verified by domain experts. When deployed without problem‑specific guidance on roughly 3,800 open problems from four paper sets, Bolzano solved about 200 of them, including four questions from papers accepted to the STOC 2026 conference, which were confirmed by the authors.
By Adri\'an Z\'ame\v{c}n\'ik, Mat\v{e}j Kripner, Martin Kouteck\'y, Martin Balko, Jan Greb\'ik, Pavel Hub\'a\v{c}ek, Robert \v{S}\'amal, V\'aclav Rozho\v{n}
SciRerankBench is a benchmark designed to evaluate rerankers in retrieval‑augmented large language models (RAG‑LLMs) for scientific literature question answering. It covers five scientific subjects and introduces three types of question‑context‑answer pairs—Noisy Contexts, Semantically Similar but Logically Irrelevant Contexts, and Counterfactual Contexts—to test noise resilience, relevance disambiguation, and factual consistency. The study evaluates 13 popular rerankers across five LLM families, offering detailed insights into their strengths and limitations.
By Haotian Chen, Qingqing Long, Meng Xiao, Xiao Luo, Wei Ju, Chengrui Wang, Yuanchun Zhou, Xuezhi Wang, Hengshu Zhu