- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper presents a researcher-in-the-loop framework combining LLM-based program evolution with exact evaluation and mathematical generalization to discover entanglement-assisted quantum error-correcting codes (EAQECCs). Starting from finite qubit constructions generated by evolved programs, researchers generalize the results to a general code family, with key algebraic properties formalised and checked. The overall approach closes 54 open gaps in standard EAQECC reference tables and includes DRAT-certified nonexistence proofs for selected parameter bounds. Controlled generation experiments demonstrate that iterative feedback improves program success rates on longer, unseen code lengths.
Critical strengths
- The mathematical generalization from finite computational discoveries into an infinite code family is a solid contribution that closes 54 listed table gaps and is formally verified in Lean. 2. The empirical ablation setup is rigorous, using controlled generation blocks and held-out code lengths to cleanly demonstrate the benefit of iterative feedback in program evolution.
Critical weaknesses
- The limitations of related work in quantum code construction and automated program evolution are not sufficiently detailed, making it hard to see where existing frameworks fail. 2. The paper lacks a detailed description clearly distinguishing novel search components from pre-existing AlphaEvolve components. 3. The specific features of quantum code discovery that make general LLM search algorithms inadequate without researcher intervention are not clearly articulated. 4. Experimental evaluations are mostly restricted to small binary parameters and specific distance targets, lacking evaluation on broader benchmark suites or larger field sizes.
Questions for authors
- Section 2.2: What specific domain characteristics of EAQECC matrix search make existing program evolution tools like FunSearch or AlphaEvolve unsuitable without researcher intervention? Please clarify what fails when running these out-of-the-box. 2. Section 3.2: Could you provide a clear top-level algorithmic description (or detailed flowchart) of the complete pipeline that explicitly separates what is built on AlphaEvolve versus what is custom-designed for quantum codes? 3. Section 3.4 & Reproducibility Statement: The setup relies on proprietary components like Vertex AI and Gemini models. How can an independent researcher without Vertex AI access reproduce the search runs and tool flow? 4. Section 4.1 & Tables 1-2: The experiments primarily focus on k=1 and low field sizes q. How does the search pipeline perform on higher dimensions (k > 2, q > 5) or more challenging code parameters? 5. Section 5.1 & Figure 4: Results are presented quite concisely. Could you add explicit lists of observations discussing why certain blocks show minimal improvement under iterative evolution compared to independent proposals?
2 comments
I would like to thank the authors for the responses. In light of the rebuttal and other reviews, I keep my score.
Response to Reviewer UyTL
AlphaEvolve requires a program, evaluator and specification. We tested EAQECC formulations, not an engine baseline. A target couples generator/Gram ranks for k,c with minimum non-radical dual weight; improving distance can violate rank. For our binary targets, dimS=2n−4 and dimS⊥=4. Dualization changes representation and moves, not the feasible code set. The initial program solves 1/64 at n=9,11. Broad dual-space advice raises independent/iterative area by +0.316/+0.346; screening then independent generation reaches 0.314 (Figure 7, §5.2). Cruz-Benito et al. also evolve quantum-code programs and prove structural results; we target EAQECC families (§2.2).
Figure 1 separates our targets, specification, initial program and evaluator from AlphaEvolve’s unmodified generation, scoring, database and parent selection. Researchers and Fable 5 analyze codes and develop checked proofs; SAT refines bounds. Magma checks parameters, DRAT-trim exclusions and Lean the algebraic core. Controlled comparisons use our Python controller with Gemini 3.5 Flash (§3).
Install
requirements.txt; in the released repository, run:These check constructions, 54 closures and study records, and replay twelve archived search lists without model access. Controlled replay needs the recorded macOS runtime. The artifact guides cover external-tool setup. Fresh generation uses Vertex/AlphaEvolve; no other backend is implemented. Please report replay issues (§3.4).
Theorem 1 covers all prime powers q≥3 at n≥2q+1 and binary odd n≥5. Eight exactly enumerated q=7 instances include [[15,1,14;7]]7. Verified examples include [[13,6,6;6]]2, [[10,1,9;4]]4 and [[12,1,11;5]]5 (§4.2, manuscript Table 2, Appendix A.2). These verify constructions; policy comparisons fix k=1,q=2. Exact evaluation enumerates qn+k−c dual vectors; dual parametrization does not remove this cost (Appendix A.1).
A block pairs generation runs: seven candidates per policy, with training/validation selection. Broad dual-space advice lets both policies implement dual search, with varying selected programs. In original replication A, run 3, iteration solves 35/64 versus 24/64 but area is 0.217 versus 0.218 because successes occur later. Policy differences are +0.099 in A (5/8 positive, p=0.33) and +0.079 in repeat B (4/8, p=0.53), neither established. Submitted Figure 4 is now Figure 6; Figure 9 shows the timing example.
Table 1 (this response). Ten-run study: behaviors among 70 candidates; area difference = iterative − independent.
Behaviors differ in recorded training score, call count, distance ratio, matrix or error. Counts are post-selection descriptions. Under search-policy advice, 69/70 independent candidates repeat one behavior; nine iterative selections add distance terms and eight change counter resets. Its area gain is positive in 10/10 runs (98.75% interval [+0.103,+0.287]); no-advice/representation differences are unestablished and objective results are near the floor. Longer-code pooled success rises from 13.4%/0.9% to 62.5%/33.4% at n=13,15 (ten programs × 32 seeds per length). The cost ratio is 1.31 without a matched-cost control. See revised Figure 4 and Appendix C.9 for results and assumptions.