LLM-Guided Quantum Code Discovery
An “AI for science” workflow that uses large language models to evolve Python programs generating quantum LDPC code designs: bivariate-bicycle (BB) and perturbed bivariate-bicycle (PBB) codes. Built on OpenEvolve with an ensemble of LLMs, and paired with an independent verification stack so every reported code is certified rather than just proposed.
Results:
- 465 distinct codes (97 CSS, 368 non-CSS) at block length n ≤ 360, from ~200K candidates screened across five campaigns — about 140 hours and ~US$400 in LLM inference
- Notable finds include an indecomposable [[288,16,12]] code, higher-rate codes reaching k = 50 at d = 8, and non-CSS codes matching the gross-code benchmark at [[144,12,12]]
- Follow-up on weight-five codes: a 1,142-entry catalogue with exact distance certificates, structural analysis, and random-search controls
Verification pipeline: GF(2) rank computation, MILP-based distance bounds, BLISS Tanner-graph deduplication, decomposability analysis, and local-Clifford equivalence checks — designed to catch the search’s own blind spots.
Presented as an invited keynote at the AI4QC workshop, IEEE Quantum Week 2026. Code, catalogues, and paper sources are open under Apache 2.0.
I research and develop AI-based systems to tackle complex problems in quantum computing and other relevant areas.
My work sits at the intersection of quantum computing, machine learning, and open source. I hold IBM Master Inventor status and have contributed to tools used by millions of developers worldwide.
I have a PhD in Computer Engineering from the University of Salamanca (2018), have authored 80+ publications, and received the 2019 SCIE-BBVA Award for best young researcher in Computer Science in Spain.