---
schema_version: "newruntime-topic-hub-v0.1"
type: "topic_hub"
slug: "retrieval"
title: "Retrieval - New Runtime"
description: "A New Runtime topic hub collecting signals, patterns, field notes, and public sources about retrieval."
answer: ["Retrieval is tracked here as an evidence-linked topic, not as a static glossary entry.","The page connects raw observations to pattern hypotheses, longer analysis, and public sources.","Use it as the canonical landing page before drilling into individual records."]
search_intents: ["retrieval","retrieval AI agents","retrieval software"]
status: "tracked"
last_updated: "2026-07-15"
counts: {"total":5,"signals":5,"patterns":0,"posts":0,"atlas":0,"sources":6}
routes: {"html":"https://newruntime.com/topics/retrieval/","markdown":"https://newruntime.com/topics/retrieval.md","json":"https://newruntime.com/topics/retrieval.json"}
top_sources: ["https://aclanthology.org/2024.acl-long.747","https://arxiv.org/abs/2410.10813","https://github.com/cocoindex-io/cocoindex","https://linkedin.com/blog/engineering/ai/semantic-search-for-ai-agents-at-scale-retrieval-and-ranking-for-linkedins-hiring-assistant","https://research.google/blog/thinking-to-recall-how-reasoning-unlocks-parametric-knowledge-in-llms","https://research.google/blog/unlocking-dependable-responses-with-gemini-enterprise-agent-platforms-agentic-rag"]
---

# Retrieval - New Runtime

A New Runtime topic hub collecting signals, patterns, field notes, and public sources about retrieval.

## Short Answer

- Retrieval is tracked here as an evidence-linked topic, not as a static glossary entry.
- The page connects raw observations to pattern hypotheses, longer analysis, and public sources.
- Use it as the canonical landing page before drilling into individual records.

## Patterns


## Field Notes


## Recent Raw Signals

- 2026-07-15: [Retrieval and long context do not create company memory](https://newruntime.com/signals/retrieval-does-not-create-company-memory/)
- 2026-07-01: [LinkedIn Builds Semantic Search for a Hiring Agent at Scale](https://newruntime.com/signals/linkedin-builds-semantic-search-for-a-hiring-agent-at-scale/)
- 2026-07-01: [Reasoning can act as self-retrieval](https://newruntime.com/signals/reasoning-can-unlock-parametric-memory/)
- 2026-06-18: [Google Makes RAG Search Again Before It Answers](https://newruntime.com/signals/google-makes-rag-search-again-before-it-answers/)
- 2026-05-06: [CocoIndex Keeps Agent Context Fresh Without Full Reindexing](https://newruntime.com/signals/cocoindex-keeps-agent-context-fresh-without-full-reindexing/)

## Public Sources

- https://aclanthology.org/2024.acl-long.747
- https://arxiv.org/abs/2410.10813
- https://github.com/cocoindex-io/cocoindex
- https://linkedin.com/blog/engineering/ai/semantic-search-for-ai-agents-at-scale-retrieval-and-ranking-for-linkedins-hiring-assistant
- https://research.google/blog/thinking-to-recall-how-reasoning-unlocks-parametric-knowledge-in-llms
- https://research.google/blog/unlocking-dependable-responses-with-gemini-enterprise-agent-platforms-agentic-rag