aiqbench analysis
This research addresses a critical bottleneck in AI-assisted quantum computing by formalizing "knowledge externalization," where implicit conventions like gauge choices and fermionic signs are converted into explicit specifications before code generation. The study demonstrates that this human-in-the-loop workflow significantly improves success rates for complex many-body tasks, such as DMRG and Pfaffian-MPS conversions, proving that content precision matters more than document formatting. By establishing an auditable protocol for translating scientific papers into executable quantum algorithms, the work provides a robust framework to reduce hallucinations in high-stakes physics simulations.
From Paper to Program: Knowledge Externalization for AI-Assisted Quantum Many-Body Code Generation
arXiv:2604.04089v3 Announce Type: replace-cross Abstract: Large language models can write scientific code, but direct paper-to-program translation remains fragile when correctness depends on tacit conventions in the literature. We identify this bottleneck as \textbf{knowledge externalization}: converting implicit computational assumptions -- index conventions, gauge choices, fermionic signs, contraction order, and memory constraints -- into an explicit technical specification before implementation. We evaluate a multi-stage, human-in-the-loop workflow that inserts such a specification, with validation and stop gates, between theory extraction and code generation. The workflow is tested on two algorithmically distinct quantum many-body tasks: variational sweep-based Density-Matrix Renormalization Group (DMRG) from a pedagogical review and constructive Pfaffian conversion of Hartree--Fock--Bogoliubov states to matrix product states from the five-page Letter by Jin et al., Phys. Rev. B 105, L081101 (2022), for which no public code is available. For DMRG, all 16 specification-guided model pairings in a $4\times4$ grid satisfy physics-validation criteria, compared with 6/13 direct attempts. A prose-specification ablation indicates that externalized content, not \LaTeX{} formatting, is the essential ingredient. For Pfaffian-MPS, the workflow succeeds in 11/26 archived attempts, whereas direct prompting yields zero audited passes. Cross-specification transfer is asymmetric: non-GPT specifications implemented by GPT~5.5 pass 4/4, while GPT~5.5 specifications implemented by weaker models fail 4/4, indicating a residual implementation-model bottleneck. The resulting \emph{Paper-to-Program Many-Body} skill provides an auditable protocol for AI-assisted implementation of many-body algorithms and for diagnosing where externalization succeeds or fails.
Abstract:Large language models can write scientific code, but direct paper-to-program translation remains fragile when correctness depends on tacit conventions in the literature. We identify this bottleneck as \textbf{knowledge externalization}: converting implicit computational assumptions -- index conventions, gauge choices, fermionic signs, contraction order, and memory constraints -- into an explicit technical specification before implementation. We evaluate a multi-stage, human-in-the-loop workflow that inserts such a specification, with validation and stop gates, between theory extraction and code generation. The workflow is tested on two algorithmically distinct quantum many-body tasks: variational sweep-based Density-Matrix Renormalization Group (DMRG) from a pedagogical review and constructive Pfaffian conversion of Hartree--Fock--Bogoliubov states to matrix product states from the five-page Letter by Jin et al., Phys. Rev. B 105, L081101 (2022), for which no public code is available. For DMRG, all 16 specification-guided model pairings in a $4\times4$ grid satisfy physics-validation criteria, compared with 6/13 direct attempts. A prose-specification ablation indicates that externalized content, not \LaTeX{} formatting, is the essential ingredient. For Pfaffian-MPS, the workflow succeeds in 11/26 archived attempts, whereas direct prompting yields zero audited passes. Cross-specification transfer is asymmetric: non-GPT specifications implemented by GPT~5.5 pass 4/4, while GPT~5.5 specifications implemented by weaker models fail 4/4, indicating a residual implementation-model bottleneck. The resulting \emph{Paper-to-Program Many-Body} skill provides an auditable protocol for AI-assisted implementation of many-body algorithms and for diagnosing where externalization succeeds or fails.
Computational Physics (physics.comp-ph); Strongly Correlated Electrons (cond-mat.str-el); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
arXiv:2604.04089 [physics.comp-ph]
(or arXiv:2604.04089v3 [physics.comp-ph] for this version)
Full text under the publisher's open licence · 246 words