Layer diagrams and decomposition in this document are original synthesis for teaching. The entries below anchor technical claims about agents, tools, retrieval, evaluation, safety, and platform practice in peer-reviewed research, official standards, and widely adopted specifications. Verify instrument texts and vendor docs before compliance or production design work.

Agentic reasoning, planning, and reflection

1. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. “ReAct: Synergizing Reasoning and Acting in Language Models.” arXiv preprint arXiv:2210.03629, 2022.
   https://arxiv.org/abs/2210.03629
2. Wei, J., Wang, X., Schuurmans, D., et al. “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.” Advances in Neural Information Processing Systems (NeurIPS), 2022.
   https://arxiv.org/abs/2201.11903
3. Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., & Yao, S. “Reflexion: Language Agents with Verbal Reinforcement Learning.” arXiv preprint arXiv:2303.11366, 2023.
   https://arxiv.org/abs/2303.11366

Tool use, skills, and environment interfaces

1. Schick, T., Dwivedi-Yu, J., Dessì, R., et al. “Toolformer: Language Models Can Teach Themselves to Use Tools.” arXiv preprint arXiv:2302.04761, 2023.
   https://arxiv.org/abs/2302.04761
2. Anthropic et al. Model Context Protocol (MCP) — open standard for model-to-tool and model-to-data integration.
   https://modelcontextprotocol.io/ · Specification (GitHub)
3. Paranjape, B., Lundberg, S., Singh, S., et al. “ART: Automatic multi-step reasoning and tool-use for large language models.” arXiv preprint arXiv:2303.09014, 2023.
   https://arxiv.org/abs/2303.09014

Retrieval, knowledge, and memory architectures

1. Lewis, P., Perez, E., Piktus, A., et al. “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.” NeurIPS, 2020. arXiv:2005.11401.
   https://arxiv.org/abs/2005.11401
2. Packer, C., Fang, V., Patil, S. G., Lin, K., Stoica, I., & Gonzalez, J. E. “MemGPT: Towards LLMs as Operating Systems.” arXiv preprint arXiv:2310.08560, 2023.
   https://arxiv.org/abs/2310.08560
3. Gao, Y., Xiong, Y., Gao, X., et al. “Retrieval-Augmented Generation for Large Language Models: A Survey.” arXiv preprint arXiv:2312.10997, 2023–2024.
   https://arxiv.org/abs/2312.10997

Multi-agent systems and coordination

1. Wu, Q., Bansal, S., Zhang, J., et al. “AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation.” arXiv preprint arXiv:2308.08155, 2023.
   https://arxiv.org/abs/2308.08155
2. Hong, S., Zheng, X., Chen, J., et al. “MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework.” arXiv preprint arXiv:2308.00352, 2023.
   https://arxiv.org/abs/2308.00352
3. Wooldridge, M. J. An Introduction to MultiAgent Systems (2nd ed.). Wiley, 2009. — classical foundations for coordination, negotiation, and distributed decision-making.

Evaluation, benchmarks, and holistic model assessment

1. Liang, P., Bommasani, R., Lee, T., et al. “Holistic Evaluation of Language Models (HELM).” arXiv preprint arXiv:2211.09110, 2022.
   https://arxiv.org/abs/2211.09110
2. Hendrycks, D., Burns, C., Basart, S., et al. “Measuring Massive Multitask Language Understanding.” ICLR, 2021. arXiv:2009.03300.
   https://arxiv.org/abs/2009.03300

Security, abuse, and trustworthy deployment

1. OWASP Foundation. OWASP Top 10 for Large Language Model Applications.
   https://owasp.org/www-project-top-10-for-large-language-model-applications/
2. Greshake, K., Abdelnabi, S., Mishra, S., et al. “Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.” arXiv preprint arXiv:2302.12173, 2023.
   https://arxiv.org/abs/2302.12173
3. Mitchell, M., et al. “Model Cards for Model Reporting.” FAT*, 2019. arXiv:1810.03993.
   https://arxiv.org/abs/1810.03993
4. Amodei, D., Olah, C., Steinhardt, J., et al. “Concrete Problems in AI Safety.” arXiv preprint arXiv:1606.06565, 2016.
   https://arxiv.org/abs/1606.06565

Regulation, risk management, and management-system standards

1. European Parliament and Council. Regulation (EU) 2024/1689 (Artificial Intelligence Act). EUR-Lex.
   https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX%3A32024R1689
2. NIST. Artificial Intelligence Risk Management Framework (AI RMF 1.0), NIST AI 100-1, 2023.
   https://doi.org/10.6028/NIST.AI.100-1
3. NIST. Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile, NIST AI 600-1, 2024.
   NIST.AI.600-1 (PDF)
4. ISO/IEC JTC 1/SC 42. ISO/IEC 42001:2023 — Artificial intelligence — Management system.
   ISO store: ISO/IEC 42001:2023

Observability, platform economics, and supply chain

1. OpenTelemetry Project. OpenTelemetry Specification — vendor-neutral traces, metrics, logs (foundation for LLM/agent tracing).
   https://opentelemetry.io/docs/specs/otel/
2. FinOps Foundation. FinOps Framework — unit economics and cloud financial accountability (applies to inference and GPU spend).
   https://www.finops.org/framework/
3. OpenSSF. SLSA: Supply-chain Levels for Software Artifacts — integrity controls for build and release pipelines.
   https://slsa.dev/