Acknowledgments & citation
Citing TeXRA
If TeXRA was useful in your research, you can cite the position paper behind it (an acknowledgment or citation is appreciated, not required):
@inproceedings{lu2026theoretical,
title = {Can Theoretical Physics Research Benefit from Language Agents?},
author = {Lu, Sirui and Jin, Zhijing and Zhang, Terry Jingchen and Kos, Pavel and Cirac, J. Ignacio and Sch{\"o}lkopf, Bernhard},
booktitle = {International Conference on Machine Learning (ICML)},
year = {2026},
eprint = {2506.06214},
archivePrefix = {arXiv}
}Supporting TeXRA
If TeXRA helps you push a derivation through, check a proof, or finish a paper sooner, you can support its development:
Research produced with TeXRA
A selection of work by the TeXRA team and collaborators that uses these multi-agent workflows (more projects and papers are listed on Work produced with TeXRA):
Lu, S., Jin, Z., Zhang, T. J., Kos, P., Cirac, J. I., & Schölkopf, B. (2026). Can Theoretical Physics Research Benefit from Language Agents? International Conference on Machine Learning (ICML 2026). The position paper on how language agents can accelerate theoretical and computational physics.
He, X., Lu, S., & Zeng, B. (2025). Co-Designing Quantum Codes with Transversal Diagonal Gates via Multi-Agent Systems. arXiv:2510.20728. Pairs symbolic synthesis and search with Lean 4 formal verification to produce a certified catalogue of 14,116 nonadditive quantum codes with prescribed transversal diagonal gates, resolving the transversal-$T$ problem for distance-3 codes.
Lu, S., Tjoa, E., & Cirac, J. I. (2026). Multi-agent Autoformalization of Tensor Network Theory. arXiv:2607.07857. Autoformalizes the fundamental theorem of matrix-product states in Lean 4 with a team of specialist agents in TeXRA and releases the TNLean library.
If you used TeXRA in your own work, open an issue or pull request on GitHub or write to contact@texra.ai.