参考文献

1. D. Sculley et al., 《Hidden Technical Debt in Machine Learning Systems》, NeurIPS, 2015.
2. A. Vaswani et al., 《Attention Is All You Need》, NeurIPS, 2017.
3. J. Xin et al., 《DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference》, ACL, 2020, arXiv:2004.12993.
4. E. Ries, The Lean Startup, Crown Business, 2011.
5. J. Humble & D. Farley, Continuous Delivery, Addison-Wesley, 2010.
6. N. Forsgren, J. Humble, and G. Kim, Accelerate: The Science of Lean Software and DevOps, IT Revolution, 2018.
7. T. Mikolov et al., 《Efficient Estimation of Word Representations in Vector Space》, arXiv:1301.3781, 2013.
8. D. Blei et al., 《Latent Dirichlet Allocation》, JMLR, 2003.
9. M. Grootendorst, 《BERTopic: Neural Topic Modeling with a Class-Based TF-IDF Procedure》, EMNLP, 2022.
10. J. S. Park et al., 《Generative Agents: Interactive Simulacra of Human Behavior》, arXiv:2304.03442, 2023.
11. ISO/IEC/IEEE International Standard - Systems and software engineering -- Life cycle processes -- Requirements engineering (IEEE Std 29148-2018), 2018, DOI: 10.1109/IEEESTD.2018.8559686.
12. UML 2.5 Specification, OMG, 2015.
13. E. Evans, Domain-Driven Design, Addison-Wesley, 2003.
14. P. Isola et al., 《Image-to-Image Translation with Conditional GANs》, CVPR, 2017.
15. H. Nguyen et al., 《Text-to-UI Generation for Web Applications》, UIST, 2023.
16. J. Nielsen, Usability Engineering, Morgan Kaufmann, 1993.
17. W3C, Web Content Accessibility Guidelines (WCAG) 2.2, 2023.
18. K. Beck, Test-Driven Development: By Example, Addison-Wesley, 2002.
19. GitHub, 《Copilot Trust Center》, 2023.
20. L. Richardson & S. Ruby, RESTful Web Services, O'Reilly, 2007.
21. S. Tilkov & S. Vinoski, 《Node.js: Using JavaScript to Build High-Performance Network Programs》, IEEE Internet Computing, 2010.
22. D. Hardt, 《The OAuth 2.0 Authorization Framework》, RFC 6749, 2012.
23. PCI Security Standards Council, Payment Card Industry Data Security Standard v4.0, 2022.
24. P. Lewis et al., 《Retrieval-Augmented Generation for Knowledge-Intensive NLP》, NeurIPS, 2020.
25. J. Johnson et al., 《Billion-Scale Similarity Search with GPUs》, IEEE Trans. Big Data, 2019.
26. J. Devlin et al., 《BERT: Pre-training of Deep Bidirectional Transformers》, NAACL, 2019.
27. S. Robertson & H. Zaragoza, 《The Probabilistic Relevance Framework: BM25 and Beyond》, Foundations and Trends in IR, 2009.
28. P. Li et al., 《RAGAS: Automated Evaluation of Retrieval-Augmented Generation》, arXiv:2402.01761, 2024.
29. S. Yao et al., 《ReAct: Synergizing Reasoning and Acting in Language Models》, ICLR, 2023.
30. Q. Wu et al., 《AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation》, arXiv:2308.08155, 2023.
31. OpenAI, 《Function Calling and Tool Use》, 2023.
32. C. Yeh et al., 《ChartLLM: A Benchmark for Chart Reasoning》, EMNLP, 2023.
33. A. Zhang et al., Dive into Deep Learning, 2021.
34. T. Gebru et al., 《Datasheets for Datasets》, CACM, 2021.
35. S. Mouli et al., 《Data Deduplication for Large Language Models》, arXiv:2307.03195, 2023.
36. Y. Wang et al., 《Self-Instruct: Aligning Language Models with Self-Generated Instructions》, ACL, 2023.
37. A. Gu et al., 《Domain Adaptation of Language Models via Continued Pretraining》, ACL, 2021.
38. R. Sennrich et al., 《Neural Machine Translation of Rare Words with Subword Units》, ACL, 2016.
39. S. Narayanan et al., 《Efficient Large-Scale Language Model Training on GPU Clusters》, MLSys, 2021.
40. E. Hu et al., 《LoRA: Low-Rank Adaptation of Large Language Models》, ICLR, 2022.
41. L. Ouyang et al., 《Training Language Models to Follow Instructions with Human Feedback》, NeurIPS, 2022.
42. S. Rafailov et al., 《Direct Preference Optimization: Your Language Model is Secretly a Reward Model》, NeurIPS, 2023.
43. T. Schick et al., 《Toolformer: Language Models Can Teach Themselves to Use Tools》, arXiv:2302.04761, 2023.
44. D. Patterson et al., 《Carbon Emissions and Large Neural Network Training》, arXiv:2104.10350, 2021.
45. H. Kwon et al., 《vLLM: Fast and Cheap LLM Serving with PagedAttention》, SOSP, 2023.
46. NVIDIA, 《TensorRT-LLM Technical Overview》, Whitepaper, 2023.
47. T. Dettmers et al., 《QLoRA: Efficient Finetuning of Quantized LLMs》, NeurIPS, 2023.
48. M. Frantar et al., 《GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers》, ICLR, 2024.
49. Hugging Face, 《Text Generation Inference: Scalable Serving》, Whitepaper, 2023.
50. H. Zheng et al., 《Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena》, NeurIPS, 2023.
51. J. Rawte et al., 《Guardrails for Generative AI》, arXiv:2307.08715, 2023.
52. E. Raymond, The Cathedral and the Bazaar, O'Reilly, 1999.
53. W3C Design Tokens Community Group, Design Tokens Format Module, Draft, https://www.designtokens.org/TR/drafts/format/, accessed 2025-12-16.
54. Deque Systems, axe-core, documentation, https://github.com/dequelabs/axe-core, accessed 2025-12-16.
55. Google, Lighthouse, documentation, https://developer.chrome.com/docs/lighthouse/, accessed 2025-12-16.
56. Storybook, Writing Tests: Test Runner, documentation, https://storybook.js.org/docs/writing-tests/integrations/test-runner, accessed 2025-12-16.
57. Microsoft, Playwright, documentation, https://playwright.dev/, accessed 2025-12-16.
58. W3C, CSS Writing Modes Level 3, Recommendation, 2019, https://www.w3.org/TR/css-writing-modes-3/.
59. J. Lin et al., 《AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration》, arXiv:2306.00978, 2023.
60. LangChain, LangGraph, documentation, https://langchain-ai.github.io/langgraph/, accessed 2025-12-16.
61. OpenTelemetry, OpenTelemetry Documentation, https://opentelemetry.io/docs/, accessed 2025-12-16.
62. Prometheus Authors, Prometheus Documentation, https://prometheus.io/docs/introduction/overview/, accessed 2025-12-16.
63. KServe Authors, KServe Documentation, https://kserve.github.io/website/, accessed 2025-12-16.
64. Grafana Labs, Grafana Documentation, https://grafana.com/docs/grafana/latest/, accessed 2025-12-16.
65. Stoplight, Spectral (OpenAPI linter), documentation, https://github.com/stoplightio/spectral, accessed 2025-12-16.
66. C. Xu et al., 《WizardLM: Empowering large pre-trained language models to follow complex instructions》, arXiv:2304.12244, 2023.
67. OpenAPI Initiative, OpenAPI Specification, https://spec.openapis.org/oas/latest.html, accessed 2025-12-16.
68. OWASP Foundation, Application Security Verification Standard (ASVS), https://owasp.org/www-project-application-security-verification-standard/, accessed 2025-12-16.
69. OpenID Foundation, OpenID Connect Core 1.0, https://openid.net/specs/openid-connect-core-1_0.html, accessed 2025-12-16.
70. IETF, 《JSON Web Token, JWT》, RFC 7519, 2015, https://www.rfc-editor.org/rfc/rfc7519, accessed 2025-12-16.
71. S. Amershi et al., 《Guidelines for Human-AI Interaction》, CHI, 2019, https://www.microsoft.com/en-us/research/publication/guidelines-for-human-ai-interaction/, accessed 2025-12-18.
72. Google PAIR, People + AI Guidebook, https://pair.withgoogle.com/guidebook/, accessed 2025-12-18.
73. T. Torres, Continuous Discovery Habits, https://www.producttalk.org/continuous-discovery-habits/, accessed 2025-12-18.
74. S. Bradner, 《Key words for use in RFCs to Indicate Requirement Levels》, RFC 2119, 1997, https://www.rfc-editor.org/rfc/rfc2119, accessed 2025-12-18.
75. Stripe, Usage-based billing, https://docs.stripe.com/billing/subscriptions/usage-based, accessed 2025-12-18.
76. Google, Site Reliability Engineering: Service Level Objectives, https://sre.google/sre-book/service-level-objectives/, accessed 2025-12-18.
77. NIST, AI Risk Management Framework (AI RMF), https://www.nist.gov/itl/ai-risk-management-framework, accessed 2025-12-18.
78. IETF, 《HTTP Semantics》, RFC 9110, 2022, https://www.rfc-editor.org/rfc/rfc9110, accessed 2025-12-18.
79. IETF, 《Problem Details for HTTP APIs》, RFC 9457, 2023, https://www.rfc-editor.org/rfc/rfc9457, accessed 2025-12-18.
80. Nielsen Norman Group, The User Experience of Customer-Service Chat: 20 Guidelines, https://www.nngroup.com/articles/chat-ux/, accessed 2025-12-19.
81. Nielsen Norman Group, Prompt Controls in GenAI Chatbots: 4 Main Uses and Best Practices, https://www.nngroup.com/articles/prompt-controls-genai/, accessed 2025-12-19.
82. Nielsen Norman Group, Testing AI with Real Design Scenarios: Evaluation Methodology and Prompts, https://www.nngroup.com/articles/testing-ai-methodology/, accessed 2025-12-19.
83. Nielsen Norman Group, Good from Afar, But Far from Good: AI Prototyping in Real Design Contexts, https://www.nngroup.com/articles/ai-prototyping/, accessed 2025-12-19.
84. Nielsen Norman Group, Leverage AI for Mock Tables and Charts When Testing Prototypes, https://www.nngroup.com/articles/ai-data-prototype-testing/, accessed 2025-12-19.
85. J. Schulman et al., 《Proximal Policy Optimization Algorithms》, arXiv:1707.06347, 2017, https://arxiv.org/abs/1707.06347.
86. P. F. Christiano et al., 《Deep Reinforcement Learning from Human Preferences》, NeurIPS, 2017, https://arxiv.org/abs/1706.03741.
87. D. Ziegler et al., 《Fine-Tuning Language Models from Human Preferences》, arXiv:1909.08593, 2019, https://arxiv.org/abs/1909.08593.
88. N. Stiennon et al., 《Learning to Summarize from Human Feedback》, NeurIPS, 2020, https://arxiv.org/abs/2009.01325.
89. Y. Bai et al., 《Constitutional AI: Harmlessness from AI Feedback》, arXiv:2212.08073, 2022, https://arxiv.org/abs/2212.08073.
90. D. Amodei et al., 《Concrete Problems in AI Safety》, arXiv:1606.06565, 2016, https://arxiv.org/abs/1606.06565.