References & Further Reading

The research this course draws on. These are the works actually cited in the units — follow the sources; the course’s opinions should belong to the literature, not its author. arXiv links are given where the citing unit provides an ID; where it does not, the venue is listed as written.

Papers

• CoALA — Sumers et al. (TMLR 2024). arXiv:2309.02427 . The memory taxonomy and “memory as a core architectural component” frame — Unit 1 .
• Reflexion — Shinn et al. (NeurIPS 2023). arXiv:2303.11366 . Verbal self-feedback stored and reused as memory — Unit 1 .
• MemGPT — Packer et al. (2023). arXiv:2310.08560 . A layered store, OS-style virtual memory for agents — Unit 2 .
• GraphRAG — Edge et al. (Microsoft, 2024). arXiv:2404.16130 . Graph-based retrieval-augmented generation — Unit 4 .
• HippoRAG 2 — Gutiérrez et al. (ICML 2025). arXiv:2502.14802 . Graph retrieval gains over the vector baseline — Unit 4 .
• GraphRAG-Bench — Xiang et al. (ICLR 2026). arXiv:2506.05690 . The cost a graph adds on simple fact lookups — Unit 4 .
• Zep / Graphiti — Rasmussen et al. (2025). arXiv:2501.13956 . A bi-temporal graph memory system — Units 5 , 6 , 11 .
• Generative Agents — Park et al. (UIST 2023). arXiv:2304.03442 . Retrieval as recency + importance + relevance — Unit 7 .
• MemoryBank — Zhong et al. (AAAI 2024). Ebbinghaus-curve forgetting applied to an agent — Unit 8 .
• A-MEM — Xu et al. (NeurIPS 2025). Curation and lifecycle of an agent memory store — Unit 8 .
• LoCoMo — Maharana et al. (ACL 2024). A very-long-conversation benchmark — Unit 9 .
• LongMemEval — Wu et al. (ICLR 2025). A benchmark of distinct memory abilities — Unit 9 .
• Mem0 — Chhikara et al. (2025). arXiv:2504.19413 . Extract, consolidate, and retrieve salient memories — Unit 11 .