Relaylit/Topics/Retrieval-augmented generation
AI & ML

Retrieval-augmented generation

Hybrid retrievers, late interaction, evaluation, long-context.

RAG is the most widely deployed LLM pattern outside chatbots. New work advances retrievers (ColBERT, SPLADE, hybrid), long-context handling, and production evaluation. Relaylit surfaces the research that's actually useful to people building RAG in production.

Example brief

"Retrieval-augmented generation with hybrid retrievers and late-interaction re-ranking. Production-oriented work."

Paste this into your Relaylit profile and tweak. First digest arrives within hours.

Where Relaylit searches for this topic

arXiv

2.4M+ preprints in physics, mathematics, computer science, and quantitative disciplines.

Semantic Scholar

200M+ academic papers with citation graphs and AI-extracted metadata across disciplines.

How Relaylit tracks retrieval-augmented generation

1. Describe it once

Paste a plain-language brief for retrieval-augmented generation. No boolean operators, no saved-search syntax.

2. We search 2 databases

Relaylit queries arXiv and Semantic Scholar on the live APIs, deduplicates the results, and ranks each paper against your brief.

3. Read the digest

A focused, ranked email lands weekly, biweekly, or monthly — the strongest retrieval-augmented generation work, not a raw feed.

Frequently asked questions

Which research databases does Relaylit search for retrieval-augmented generation?

Relaylit searches arXiv and Semantic Scholar for retrieval-augmented generation. Every result is pulled from the live APIs each time your digest is generated, so new work reaches you within hours of being indexed.

How often will I get retrieval-augmented generation updates?

You choose the cadence — weekly, biweekly, or monthly. Each digest ranks every new match against your brief and emails you a focused, ranked selection instead of a raw feed.

Can I customise what counts as relevant?

Yes. You write a plain-language brief — for example: "Retrieval-augmented generation with hybrid retrievers and late-interaction re-ranking. Production-oriented work." — and Relaylit ranks every result against it. Tighten or broaden the brief any time.

Is tracking retrieval-augmented generation free?

Relaylit is free for up to two topics, so you can track retrieval-augmented generation at no cost. Paid plans add more topics and higher frequency.

Related topics

LLM agents and tool use

Multi-step agents, tool calling, memory, reliability, evaluation harnesses.

LLM evaluation and benchmarks

Benchmark design, contamination, human evals, agentic task suites.

Ready to track this?

Your first retrieval-augmented generation digest lands this week.