Vibe-Coded and Tuned: A State-of-the-Art SMT Solver for QF-LRA

13 pages•Published: October 24, 2026

Abstract

This paper presents the SMT solver primo, which is fully vibe-coded and then parameter-tuned, achieving state-of-the-art results on linear real arithmetic (QF-LRA). The performance of primo is achieved by a systematic literature survey, repeated profiling, and parameter tuning. The resulting solver outperforms the winner of the QF-LRA track of SMT-COMP 2026. This confirms that vibe-coding of automated reasoning tools will enable us to make great strides in the future.

In: Stephan Schulz, Konstantin Korovin and Michael Rawson (editors). Proceedings of 16th International Workshop on the Implementation on Logics. Proceedings of the 26th Conference on Logic for Programming, Artificial Intelligence, and Reasoning (short papers), vol 23, pages 44-56.

Links:	https://easychair.org/publications/paper/rPZ9
	https://doi.org/10.29007/rn52

BibTeX entry

@inproceedings{IWIL-2026:Vibe_Coded_Tuned_State,
  author    = {Mikoláš Janota and Jan Jakubův},
  title     = {Vibe-Coded and Tuned: A State-of-the-Art SMT Solver for QF-LRA},
  booktitle = {Proceedings of 16th International Workshop on the Implementation on Logics. Proceedings of the 26th Conference on Logic for Programming, Artificial Intelligence, and Reasoning (short papers)},
  editor    = {Stephan Schulz and Konstantin Korovin and Michael Rawson},
  series    = {Kalpa Publications in Computing},
  volume    = {23},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2515-1762},
  url       = {/publications/paper/rPZ9},
  doi       = {10.29007/rn52},
  pages     = {44-56},
  year      = {2026}}

Download PDF Open PDF in browser