Skip to content

Bibliography

Sanitized, publishable reference library for the research publication set. See ../../internal/bibliography-internal.md for working annotations and Eden-specific notes.

Multi-agent systems and agentic workflows

  • Wei, J., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. NeurIPS 2022.
  • Wang, L., et al. (2024). A survey on large language model based autonomous agents. Frontiers of Computer Science.
  • Xi, Z., et al. (2023). The rise and potential of large language model based agents: A survey. arXiv:2309.07864.
  • Park, J. S., et al. (2023). Generative agents: Interactive simulacra of human behavior. ACM UIST 2023.

Memory for agents

  • Generative Agents memory stream (reflection, retrieval, importance) — Park et al., 2023.
  • MemGPT / Letta, Zep — persistent memory backends for conversational agents. (Compare as product-layer memory systems, not as deployment infrastructure.)
  • Open Knowledge Format (OKF) v0.1 — Google. File-format layer for portable structured knowledge; compare at format layer, not runtime layer.

Systems and operations

  • Beyer, B., et al. (2016). Site Reliability Engineering: How Google Runs Production Systems. O'Reilly.
  • Gawande, A. (2009). The Checklist Manifesto: How to Get Things Right. Metropolitan Books.
  • Limoncelli, T. A., et al. (2014). The Practice of Cloud System Administration. Addison-Wesley.

Evaluation

  • Hendrycks, D., et al. (2021). Measuring massive multitask language understanding. ICLR 2021.
  • Liu, X., et al. (2023). AgentBench: Evaluating LLMs as agents. ICLR 2024.
  • Jimenez, C., et al. (2023). SWE-bench: Can language models resolve real-world GitHub issues? NeurIPS 2023 Datasets and Benchmarks.
  • Zheng, L., et al. (2023). Judging LLM-as-a-judge with MT-bench and chatbot arena. NeurIPS 2023.

Agent coordination and roles

  • AutoGen / Multi-Agent Conversation Framework (Microsoft Research).
  • CrewAI — role-based agent crews.
  • DSPy — declarative language model programming and optimizers.

To do

  • [ ] Add one-paragraph annotation per entry explaining relevance to the publication set.
  • [ ] Categorize entries by paper (field study, failure modes, taxonomy, position, evaluation).
  • [ ] Add practitioner/operations references (e.g., incident command, post-mortem templates).
  • [ ] Export final version to public/mini-site/docs/artifacts/bibliography.md once papers are complete.