Referencias

Anthropic (25 de noviembre de 2024). Introducing the Model Context Protocol. Anuncio oficial. Creado por David Soria Parra y Justin Spahr-Summers. Especificación en modelcontextprotocol.io.

Bender, Emily M.; Gebru, Timnit; McMillan-Major, Angelina; Shmitchell, Shmargaret (2021). On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?. Proceedings of the ACM Conference on Fairness, Accountability, and Transparency (FAccT).

Bommasani, Rishi; Hudson, Drew A.; Adeli, Ehsan; others (2021). On the Opportunities and Risks of Foundation Models. Stanford Center for Research on Foundation Models (CRFM).

Brown, Tom B.; Mann, Benjamin; Ryder, Nick; Subbiah, Melanie; others (2020). Language Models Are Few-Shot Learners. Advances in Neural Information Processing Systems (NeurIPS).

Chase, Harrison (2025). As cited in the manuscript (LangChain).

Chen, Mark; Tworek, Jerry; Jun, Heewoo; Yuan, Qiming; others (2021). Evaluating Large Language Models Trained on Code. arXiv preprint (Codex).

Conway, Melvin E. (1968). How Do Committees Invent?. Datamation.

Du, Yilun; Li, Shuang; Torralba, Antonio; Tenenbaum, Joshua B.; Mordatch, Igor (2023). Improving Factuality and Reasoning in Language Models through Multiagent Debate. arXiv preprint.

Evans, Eric (2003). Domain-Driven Design: Tackling Complexity in the Heart of Software. Addison-Wesley.

Ferber, Jacques (1999). Multi-Agent Systems: An Introduction to Distributed Artificial Intelligence. Addison-Wesley.

Fowler, Martin (2018). Refactoring: Improving the Design of Existing Code. (2nd ed.) Addison-Wesley.

Greshake, Kai; Abdelnabi, Sahar; Mishra, Shailesh; Endres, Christoph; Holz, Thorsten; Fritz, Mario (2023). Not What You’ve Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection. arXiv preprint.

Hong, Sirui; Zheng, Xiawu; Chen, Jonathan; Cheng, Yuheng; others (2024). MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework. ICLR.

Ji, Ziwei; Lee, Nayeon; Frieske, Rita; others (2023). Survey of Hallucination in Natural Language Generation. ACM Computing Surveys.

Jimenez, Carlos E.; Yang, John; Wettig, Alexander; others (2024). SWE-bench: Can Language Models Resolve Real-World GitHub Issues?. ICLR.

Kapoor, Sayash; Stroebl, Benedikt; Siegel, Zachary S.; Nadgir, Arvind; Narayanan, Arvind (2024). AI Agents That Matter. arXiv preprint.

Khattab, Omar; Singhvi, Arnav; Maheshwari, Paridhi; others (2024). DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines. International Conference on Learning Representations (ICLR).

Lewis, Patrick; Perez, Ethan; Piktus, Aleksandra; Petroni, Fabio; others (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems (NeurIPS).

Liu, Nelson F.; Lin, Kevin; Hewitt, John; Paranjape, Ashwin; Bevilacqua, Michele; Petroni, Fabio; Liang, Percy (2024). Lost in the Middle: How Language Models Use Long Contexts. Transactions of the Association for Computational Linguistics (TACL).

Madaan, Aman; Tandon, Niket; Gupta, Prakhar; Hallinan, Skyler; others (2023). Self-Refine: Iterative Refinement with Self-Feedback. Advances in Neural Information Processing Systems (NeurIPS).

Martin, Robert C. (2009). Clean Code: A Handbook of Agile Software Craftsmanship. Prentice Hall.

Martin, Robert C. (2017). Clean Architecture: A Craftsman’s Guide to Software Structure and Design. Prentice Hall.

Mitchell, Melanie; others (2025). As cited in the manuscript. Bibliographic detail not fully verified; see manuscript context.

NIST (2023). AI Risk Management Framework 1.0. National Institute of Standards and Technology.

OpenAI (12 de septiembre de 2024). Learning to Reason with LLMs. En AIME 2024, GPT-4o resolvió de media el 12 % de los problemas (1,8 de 15) y o1 el 74 % (11,1 de 15) con una sola muestra por problema.

Ouyang, Long; Wu, Jeffrey; Jiang, Xu; Almeida, Diogo; others (2022). Training Language Models to Follow Instructions with Human Feedback. Advances in Neural Information Processing Systems (NeurIPS).

Packer, Charles; Fang, Vivian; Patil, Shishir G.; Lin, Kevin; Wooders, Sarah; Gonzalez, Joseph E. (2024). MemGPT: Towards LLMs as Operating Systems. arXiv preprint.

Park, Joon Sung; O’Brien, Joseph C.; Cai, Carrie J.; Morris, Meredith Ringel; Liang, Percy; Bernstein, Michael S. (2023). Generative Agents: Interactive Simulacra of Human Behavior. arXiv preprint.

Parnas, David L. (1972). On the Criteria To Be Used in Decomposing Systems into Modules. Communications of the ACM.

Peng, Sida; Kalliamvakou, Eirini; Cihon, Peter; Demirer, Mert (2023). The Impact of AI on Developer Productivity: Evidence from GitHub Copilot. arXiv:2302.06590 [cs.SE]. Experimento controlado: el grupo con acceso al asistente completó la tarea un 55,8 % más rápido que el grupo de control.

Qian, Chen; Cong, Xin; Yang, Cheng; others (2024). ChatDev: Communicative Agents for Software Development.

Russell, Stuart; Norvig, Peter (2020). Artificial Intelligence: A Modern Approach. (4th ed.) Pearson.

Schick, Timo; Dwivedi-Yu, Jane; Dess`i, Roberto; Raileanu, Roberta; others (2023). Toolformer: Language Models Can Teach Themselves to Use Tools. Advances in Neural Information Processing Systems (NeurIPS).

Shinn, Noah; Cassano, Federico; Berman, Edward; Gopinath, Ashwin; Narasimhan, Karthik; Yao, Shunyu (2023). Reflexion: Language Agents with Verbal Reinforcement Learning. Advances in Neural Information Processing Systems (NeurIPS).

Skelton, Matthew; Pais, Manuel (2019). Team Topologies: Organizing Business and Technology Teams for Fast Flow. IT Revolution Press.

Snell, Charlie; Lee, Jaehoon; Xu, Kelvin; Kumar, Aviral (2024). Scaling LLM Test-Time Compute Optimally Can Be More Effective Than Scaling Model Parameters. arXiv preprint.

Uni'on Europea (2024). Reglamento (UE) de Inteligencia Artificial (EU AI Act).

Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; Uszkoreit, Jakob; Jones, Llion; Gomez, Aidan N.; Kaiser, Lukasz; Polosukhin, Illia (2017). Attention Is All You Need. Advances in Neural Information Processing Systems (NeurIPS).

Wang, Shawn (2023). The Rise of the AI Engineer. Latent Space (blog), as cited in the manuscript.

Wei, Jason; Wang, Xuezhi; Schuurmans, Dale; Bosma, Maarten; Ichter, Brian; Xia, Fei; Chi, Ed; Le, Quoc; Zhou, Denny (2022). Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Advances in Neural Information Processing Systems (NeurIPS).

Wooldridge, Michael (2009). An Introduction to MultiAgent Systems. (2nd ed.) Wiley.

Wu, Qingyun; Bansal, Gagan; Zhang, Jieyu; Wu, Yiran; Li, Beibin; Zhu, Erkang; et al. (2023). AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. arXiv:2308.08155 [cs.AI] (preprint, 16 de agosto de 2023; v2 en octubre de 2023).

Yao, Shunyu; Yu, Dian; Zhao, Jeffrey; Shafran, Izhak; Griffiths, Thomas L.; Cao, Yuan; Narasimhan, Karthik (2023). Tree of Thoughts: Deliberate Problem Solving with Large Language Models. Advances in Neural Information Processing Systems (NeurIPS).

Yao, Shunyu; Zhao, Jeffrey; Yu, Dian; Du, Nan; Shafran, Izhak; Narasimhan, Karthik; Cao, Yuan (2023). ReAct: Synergizing Reasoning and Acting in Language Models. International Conference on Learning Representations (ICLR).

Zheng, Lianmin; Chiang, Wei-Lin; Sheng, Ying; Zhuang, Siyuan; others (2023). Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. Advances in Neural Information Processing Systems (NeurIPS).

Ziegler, Albert; Kalliamvakou, Eirini; Li, X. Alice; Rice, Andrew; Rifkin, Devon; Simister, Shawn; Sittampalam, Ganesh; Aftandilian, Edward (2024). Measuring GitHub Copilot’s Impact on Productivity. Communications of the ACM, 67(3), 54-63._ Estudio de campo con Metric, el equipo de análisis de GitHub.

TypeSafe AI (2026). Jev: A System One Control Layer for Autonomous Agents. Architecture and Technical Specification.

OpenAI (2026). Introducing Dots: Persistent Digital Coworkers with Isolated Cloud Environments and Governed Control Planes. OpenAI DevDay 2026.