[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85798-en":3,"doc-seo-85798-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85798,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",6,"Technology","Quantum Circuit Vision Cost Aware Evaluation of Visual AI Agents for Quantum Code Generation","Quantum Circuit Vision evaluates whether multimodal AI agents can visually interpret quantum circuit diagrams and generate verified, executable code while controlling computational cost. The work builds a 132-circuit benchmark across 13 circuit categories (1–10 qubits) with Amazon Braket code execution and unitary-fidelity verification. Experiments on three Claude-family models show the mid-tier option best balances cost and accuracy. Circuit depth predicts failure; chain-of-thought prompting adds no measurable benefit. A cascade routing strategy improves accuracy at reduced cost, and releases QCV-Dataset plus reproducible evaluation code and cost logs.","Quantum Circuit Vision: Cost-Aware Evaluation of Visual AI Agents for Quantum Code Generation  \nDongping Liu§† Amazon Web Services Hong Kong, China  \nAoyu Zhang† Amazon Web Services Beijing, China  \nLuyao Zhang†∗ Duke Kunshan University Suzhou, China  \narXiv :2607 . 10057v1 [ quant-ph] 11 Jul 2026  \nAbstract  \nCan AI agents visually comprehend quantum circuit diagrams and generate verified executable code—and at what cost? We present Quantum Circuit Vision, a cost-aware evaluation framework for multimodal AI agents on quantum circuit visual understanding. We construct a 132-circuit benchmark spanning 13 categories (1–10 qubits) with executable Amazon Braket code and unitary-fidelity verification. Evaluating three frontier Claude-family models at different capability-cost tiers with 􀀽 = 5 repeated trials, we find that the mid-tier model (Sonnet 4 .6, 1 .30× credits) offers the most favorable balance on the cost–accuracy frontier: 91% pass rate on the core subset at 18% of the per-call cost of the strongest model (Opus 4.6), whose accuracy advantage is not statistically significant (paired 􀁃 : 􀀿 = 0. 083) . Logistic regression confirms that circuit depth—not qubit count—is the primary predictor of failure (􀀿 \u003C 0. 001) . Chainof-thought prompting shows no statistically significant effect (all 􀀿 > 0.18, 􀀽 = 5), suggesting that visual pattern recognition outweighs explicit reasoning strategy for structurally coupled diagrams. We propose a cascade routing strategy (cheap→ expensive models) that achieves 84% accuracy at 38% of single-model cost, demonstrating that model routing dominates prompt engineering as a cost lever. We release QCV-Dataset (132 circuits, 5 modalities, 1,931 files) on Hugging Face Hub as an open evaluation infrastructure with structured metadata for discoverability, interoperability, and responsible AI documentation, and all evaluation code, cost logs, and verification scripts on GitHub for full reproducibility.  \nKeywords  \nQuantum Computing; Multimodal LLMs; Visual Code Generation; Cost-Aware Evaluation; Benchmark  \n1 Introduction  \nThe year 2025 marked a quantum inflection point: the Nobel Prize in Physics recognized experiments with superconducting qubits that enabled macroscopic quantum coherence, while the ACM Turing Award honored the foundations of quantum information theory—including the BB84 protocol that underpins quantum key distribution. The United Nations declared 2025 the International Year of Quantum Science and Technology. Quantum computing has  \n§ Work done while at Amazon Web Services. Dongping Liu is currently with Tenorshare, Hong Kong, China.  \n†The authors are listed in alphabetical order according to last names and, then, first names. Acknowledgments: We thank the anonymous reviewers of the KDD Workshop on Evaluation and Trustworthiness of Agentic AI, KDD-2026, August 9, 2026, Jeju, South Korea for their constructive feedback, which greatly improved the quality and rigor of this work.  \n∗ The Corresponding author: Email: [lz183@duke.edu](lz183@duke.edu), Digital Innovation Research Center and Social Science Division, Duke Kunshan University, Address: Duke Avenue No.8, Kunshan, Suzhou, Jiangsu, China, 215316 .  \ncrossed from theoretical promise to engineering reality [1, 5, 21] . Concurrently, the convergence of artificial intelligence and quantum computing has emerged as a transformative research frontier, with AI techniques advancing challenges across the full quantum stack—from device design and error correction to circuit compilation and verification [3] .  \nYet a fundamental bottleneck persists: the gap between how quantum algorithms are communicated (as circuit diagrams in papers, textbooks, and courses) and how they are executed (as code in software development kits (SDKs) such as Amazon Braket [4], Qiskit [37], or Cirq) . Every quantum circuit published in a research paper must be manually translated into executable code—a tedious, error-prone process requiring both visual interpret","cbCainfvnY2XqU4L","https://ap.wps.com/l/cbCainfvnY2XqU4L","pdf",658340,1,13,"English","en",105,"# Introduction\n## Why quantum circuits, not classical?\n## Why autonomous design, not just translation?\n## Why cost-aware evaluation?","[{\"question\":\"What problem does Quantum Circuit Vision address?\",\"answer\":\"It targets the translation bottleneck between quantum circuit diagrams shown in literature and executable, verified code required by SDKs such as Amazon Braket.\"},{\"question\":\"How is the benchmark constructed and verified?\",\"answer\":\"It uses a 132-circuit benchmark spanning 13 categories with executable Amazon Braket code and unitary-fidelity verification.\"},{\"question\":\"Which model choice and strategy improve cost-effectiveness?\",\"answer\":\"The mid-tier Claude-family model provides the best cost–accuracy trade-off, and a cascade routing strategy (using cheaper models first) achieves higher accuracy at a fraction of single-model cost.\"}]",1784206336,33,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"quantum-circuit-vision-cost-aware-evaluation-of-visual-ai-agents-for-quantum-code-generation","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/quantum-circuit-vision-cost-aware-evaluation-of-visual-ai-agents-for-quantum-code-generation/85798/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Quantum Circuit Vision address?","Question",{"text":75,"@type":76},"It targets the translation bottleneck between quantum circuit diagrams shown in literature and executable, verified code required by SDKs such as Amazon Braket.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the benchmark constructed and verified?",{"text":80,"@type":76},"It uses a 132-circuit benchmark spanning 13 categories with executable Amazon Braket code and unitary-fidelity verification.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model choice and strategy improve cost-effectiveness?",{"text":84,"@type":76},"The mid-tier Claude-family model provides the best cost–accuracy trade-off, and a cascade routing strategy (using cheaper models first) achieves higher accuracy at a fraction of single-model cost.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]