Journal article · 2026 · Open access
Automated Conjecture Resolution with Formal Verification
SuperIntelligence - Robotics - Safety & Alignment, 3(3) · Published 25 September 2026 · DOI 10.70777/si.v3i3.18746
In brief
“Automated Conjecture Resolution with Formal Verification” is a 2026 journal article by Haocheng Ju and 15 co-authors, published in SuperIntelligence - Robotics - Safety & Alignment. OpenAlex counts 87 citations as of 21 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at SuperIntelligence - Robotics - Safety & Alignment.
- Citations
- 87
- Most cited in
- 2026 (87)
- Field-weighted impact
- 207.41
- References
- 48
- Authors
- 16
Abstract
Recent advances in large language models (LLMs) have significantly improved their ability to perform mathematical reasoning, extending from elementary problem solving to increasingly capable performance on research-level problems. However, reliably solving and verifying such problems remains challenging due to the inherent ambiguity of natural language reasoning. In this paper, we propose an automated framework for tackling research-level mathematical problems that integrates natural language reasoning with formal verification, enabling end-to-end problem solving with minimal human intervention. Our framework consists of two components: an informal reasoning agent, Rethlas, and a formal verification agent, Archon. Rethlas mimics the workflow of human mathematicians by combining reasoning primitives with our mathematical theorem search engine, Matlas, to explore solution strategies and construct candidate proofs. Archon, equipped with our formal theorem search engine LeanSearch, translates informal arguments into fully formalized Lean 4 projects through structured task decomposition, iterative refinement, and automated proof synthesis, ensuring machine-checkable correctness. Using this framework, we automatically resolve an open problem in commutative algebra proposed by D. D. Anderson (2014) and formally verify the resulting proof in Lean 4 with essentially no human involvement. Additional research-level case studies further illustrate the capabilities of Rethlas in informal mathematical reasoning and discovery, as well as the ability of Archon to formalize research-level proofs in Lean 4. Our experiments demonstrate that strong theorem retrieval tools enable the discovery and application of deep, cross-domain mathematical techniques, while the formal agent is capable of autonomously filling nontrivial gaps in informal arguments. More broadly, our work illustrates a promising paradigm for mathematical research in which informal and formal reasoning systems, equipped with theorem retrieval tools, operate in tandem to produce verifiable results, substantially reduce human effort, and offer a concrete instantiation of human–AI collaborative mathematical research with minimal human involvement.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Ju, H., Gao, G., Jiang, J., Wu, B., Sun, Z., Liu, S., Chen, L., Wang, Y., Wang, Z., Wang, Z., He, W., Wu, P., Xiao, L., Liu, R., Dai, B., & Dong, B. (2026). Automated Conjecture Resolution with Formal Verification. SuperIntelligence - Robotics - Safety & Alignment, 3(3). https://doi.org/10.70777/si.v3i3.18746
MLA 9
Ju, Haocheng, et al. “Automated Conjecture Resolution with Formal Verification.” SuperIntelligence - Robotics - Safety & Alignment, vol. 3, no. 3, 2026. https://doi.org/10.70777/si.v3i3.18746.
Chicago
Ju, Haocheng, Guoxiong Gao, Jiedong Jiang, Bin Wu, Zeming Sun, Shurui Liu, Leheng Chen, et al. 2026. “Automated Conjecture Resolution with Formal Verification.” SuperIntelligence - Robotics - Safety & Alignment 3 (3). https://doi.org/10.70777/si.v3i3.18746.
Harvard
Ju, H. et al. (2026) ‘Automated Conjecture Resolution with Formal Verification’, SuperIntelligence - Robotics - Safety & Alignment, 3(3). doi:10.70777/si.v3i3.18746.
IEEE
H. Ju et al., “Automated Conjecture Resolution with Formal Verification,” SuperIntelligence - Robotics - Safety & Alignment, vol. 3, no. 3, 2026, doi: 10.70777/si.v3i3.18746.
BibTeX
@article{ju2026automated,
title = {{Automated Conjecture Resolution with Formal Verification}},
author = {Ju, Haocheng and Gao, Guoxiong and Jiang, Jiedong and Wu, Bin and Sun, Zeming and Liu, Shurui and Chen, Leheng and Wang, Yuefeng and Wang, Zichen and Wang, Zichen and He, Wanyi and Wu, Peihao and Xiao, Liang and Liu, Ruochuan and Dai, Bryan and Dong, Bin},
journal = {SuperIntelligence - Robotics - Safety \& Alignment},
year = {2026},
volume = {3},
number = {3},
doi = {10.70777/si.v3i3.18746},
url = {https://doi.org/10.70777/si.v3i3.18746}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Software › Logic, programming, and type systems
- formal verification
- large language models
- mathematical reasoning
- Lean 4
- informal reasoning
- human-AI collaboration
- commutative algebra
- archons
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Ju, H., Gao, G., Jiang, J., Wu, B., Sun, Z., Liu, S., Chen, L., Wang, Y., Wang, Z., Wang, Z., He, W., Wu, P., Xiao, L., Liu, R., Dai, B., & Dong, B. (2026). Automated Conjecture Resolution with Formal Verification. SuperIntelligence - Robotics - Safety & Alignment, 3(3). https://doi.org/10.70777/si.v3i3.18746
How many times has this paper been cited?
87 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at SuperIntelligence - Robotics - Safety & Alignment: sign in and open the PDF from this page.
Who wrote this paper?
Haocheng Ju, Guoxiong Gao, Jiedong Jiang, Bin Wu, Zeming Sun, Shurui Liu, Leheng Chen, Yuefeng Wang, Zichen Wang, Zichen Wang, Wanyi He, Peihao Wu and 4 more.
What is the DOI of this paper?
10.70777/si.v3i3.18746, permanently at https://doi.org/10.70777/si.v3i3.18746. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.