# Methodology & Bibliography — Agent Memory Glossary

> Sourcing rule, freshness flags, refresh cadence, full 51-source bibliography.

Data last refreshed: 2026-05-08. Next scheduled refresh: Q3 2026, or sooner on a vendor / regulator / paper trigger.

## Sourcing rule

Every term has one canonical primary-source citation: a vendor or framework documentation page, a peer-reviewed or arXiv paper, an analyst publication where the analyst originated the framing, or a standards-body specification. Wikipedia and secondary blogs are never primary citations. When more than one canonical source could be cited, the citation is chosen by hierarchy: peer-reviewed paper > standards body > vendor primary documentation > analyst publication.

## Freshness flags

- **Foundational** — original peer-reviewed papers that anchor the field. Refreshed only if substantively revised.
- **In force** — binding standards or vendor specifications currently in effect.
- **Emerging 2026** — terms that entered mainstream discourse in 2025–2026 and are still stabilising.
- **Contested** — terms with named, meaningful disagreement in the field.

## Refresh cadence

Quarterly term audit (next: Q3 2026). Trigger-based refresh on: canonical-vendor SDK or doc page changing a term, new arXiv paper crossing the bar from emerging to load-bearing, vector-store vendor releasing a new index family, W3C / Neo4j / standards-body update, or a canonical-source URL 404-ing.

## Coverage scope

This glossary is scoped to memory architecture for LLM agents. It excludes general-purpose ML vocabulary that does not bear on agent-memory design decisions. For broader agentic-AI vocabulary see the [Agentic Glossary — Quick Reference](https://agentic-glossary-quickref.roei-020.workers.dev/); for narrative depth on flagship terms see the [deep Agentic Glossary](https://agentic-glossary.roei-020.workers.dev/).

## Bibliography (51 unique sources)

- AgentsBooks — Anatomy of a Firm — https://agentsbooks.com/anatomy — accessed 2026-05-08
- Anthropic — Building Effective Agents — https://www.anthropic.com/research/building-effective-agents — accessed 2026-05-08
- Anthropic — Claude long-context model card — https://docs.claude.com/en/docs/build-with-claude/context-windows — accessed 2026-05-08
- Anthropic — Effective context engineering for AI agents — https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents — accessed 2026-05-08 _[Emerging 2026]_
- Anthropic — Long context prompting tips — https://www.anthropic.com/news/prompting-long-context — accessed 2026-05-08
- Anthropic — Prompt caching — https://docs.claude.com/en/docs/build-with-claude/prompt-caching — accessed 2026-05-08 _[In force]_
- Asai et al. — Self-RAG (2023) — https://arxiv.org/abs/2310.11511 — accessed 2026-05-08
- Cohere — Rerank model documentation — https://docs.cohere.com/docs/rerank-overview — accessed 2026-05-08
- Cormack et al. — RRF (2009) — https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf — accessed 2026-05-08 _[Foundational]_
- Faiss — Approximate nearest neighbour wiki — https://github.com/facebookresearch/faiss/wiki — accessed 2026-05-08
- Faiss — IVF documentation — https://github.com/facebookresearch/faiss/wiki/Faiss-indexes — accessed 2026-05-08
- Gao et al. — HyDE (2022) — https://arxiv.org/abs/2212.10496 — accessed 2026-05-08
- Gartner — Hype Cycle for Agentic AI — https://www.gartner.com/en/articles/hype-cycle-for-agentic-ai — accessed 2026-05-08 _[Emerging 2026]_
- Hogan et al. — Knowledge Graphs (2021) — https://arxiv.org/abs/2003.02320 — accessed 2026-05-08 _[Foundational]_
- Izacard & Grave — Fusion-in-Decoder (2020) — https://arxiv.org/abs/2007.01282 — accessed 2026-05-08 _[Foundational]_
- Jégou et al. — Product Quantization (2011) — https://lear.inrialpes.fr/pubs/2011/JDS11/jegou_searching_with_quantization.pdf — accessed 2026-05-08 _[Foundational]_
- Karpukhin et al. — Dense Passage Retrieval (2020) — https://arxiv.org/abs/2004.04906 — accessed 2026-05-08
- LangChain — ConversationSummaryMemory — https://python.langchain.com/docs/versions/migrating_memory/conversation_summary_memory/ — accessed 2026-05-08
- LangChain — Memory in Agents — https://python.langchain.com/docs/how_to/migrate_agent/ — accessed 2026-05-08
- LangChain — Query analysis (decomposition) — https://python.langchain.com/docs/how_to/query_multiple_queries/ — accessed 2026-05-08
- LangChain — Semantic chunker — https://python.langchain.com/docs/how_to/semantic-chunker/ — accessed 2026-05-08
- Letta — Documentation — https://docs.letta.com/ — accessed 2026-05-08
- Lewis et al. — Retrieval-Augmented Generation (2020) — https://arxiv.org/abs/2005.11401 — accessed 2026-05-08 _[Foundational]_
- Liu et al. — Lost in the Middle (2023) — https://arxiv.org/abs/2307.03172 — accessed 2026-05-08 _[Foundational]_
- Malkov & Yashunin — HNSW (2018) — https://arxiv.org/abs/1603.09320 — accessed 2026-05-08 _[Foundational]_
- Mem0 — Memory architecture for AI agents — https://docs.mem0.ai/overview — accessed 2026-05-08
- Microsoft Research — GraphRAG — https://microsoft.github.io/graphrag/ — accessed 2026-05-08 _[Emerging 2026]_
- Milvus — Documentation — https://milvus.io/docs — accessed 2026-05-08
- Neo4j — Cypher Manual — https://neo4j.com/docs/cypher-manual/current/ — accessed 2026-05-08
- Neo4j — Property graph model — https://neo4j.com/docs/getting-started/appendix/graphdb-concepts/ — accessed 2026-05-08
- OpenAI — Embeddings guide — https://platform.openai.com/docs/guides/embeddings — accessed 2026-05-08
- Packer et al. — MemGPT (2023) — https://arxiv.org/abs/2310.08560 — accessed 2026-05-08 _[Foundational]_
- Park et al. — Generative Agents (2023) — https://arxiv.org/abs/2304.03442 — accessed 2026-05-08 _[Foundational]_
- pgvector — GitHub — https://github.com/pgvector/pgvector — accessed 2026-05-08
- Pinecone — Chunking strategies — https://www.pinecone.io/learn/chunking-strategies/ — accessed 2026-05-08
- Pinecone — Documentation — https://docs.pinecone.io/ — accessed 2026-05-08
- Pinecone — Reranking guide — https://docs.pinecone.io/guides/search/rerank-results — accessed 2026-05-08
- Pinecone — Similarity search — https://docs.pinecone.io/guides/search/semantic-search — accessed 2026-05-08
- Pinecone — Vector similarity explained — https://www.pinecone.io/learn/vector-similarity/ — accessed 2026-05-08
- Pinecone — What is a vector database? — https://www.pinecone.io/learn/vector-database/ — accessed 2026-05-08
- Qdrant — Documentation — https://qdrant.tech/documentation/ — accessed 2026-05-08
- Robertson & Zaragoza — BM25 (2009) — https://www.staff.city.ac.uk/~sbrp622/papers/foundations_bm25_review.pdf — accessed 2026-05-08 _[Foundational]_
- Shinn et al. — Reflexion (2023) — https://arxiv.org/abs/2303.11366 — accessed 2026-05-08 _[Foundational]_
- W3C — RDF 1.1 Primer — https://www.w3.org/TR/rdf11-primer/ — accessed 2026-05-08
- W3C — RDF Concepts — https://www.w3.org/TR/rdf11-concepts/ — accessed 2026-05-08
- W3C — SPARQL 1.1 Query Language — https://www.w3.org/TR/sparql11-query/ — accessed 2026-05-08 _[In force]_
- Wang et al. — Voyager (2023) — https://arxiv.org/abs/2305.16291 — accessed 2026-05-08
- Weaviate — Documentation — https://weaviate.io/developers/weaviate — accessed 2026-05-08
- Weaviate — Hybrid search documentation — https://weaviate.io/developers/weaviate/search/hybrid — accessed 2026-05-08
- Xu et al. — A-Mem (2025) — https://arxiv.org/abs/2502.12110 — accessed 2026-05-08 _[Emerging 2026]_
- Zhong et al. — MemoryBank (2023) — https://arxiv.org/abs/2305.10250 — accessed 2026-05-08

## Privacy and editorial discipline

Reuses the AgentsBooks portfolio controlled vocabulary (agent fleet, agentic firm, 8 primitives, complete-not-compete, auditable substrate). Voice is operator-grade, plural first-person, citation-anchored. Comparison-style claims about vendors quote the vendor's own published documentation; we do not editorialise inside a definition.

Updated 2026-05-08.