Relaylit/Topics/LLM agents and tool use
AI & ML

LLM agents and tool use

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

Track llm agents and tool use for free

Agents are the fastest-moving subarea of applied AI. Relaylit tracks arXiv (where most agent work lands first), plus Semantic Scholar and OpenAlex for cross-references, and surfaces the 5–10 papers each week that advance the SOTA or introduce useful ideas.

Example brief

"LLM agents and tool use, emphasis on reliability, multi-step planning, and evaluation. Latest work from last 6 weeks."

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.

About arXiv →

Semantic Scholar

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

About Semantic Scholar →

OpenAlex

Free, open replacement for Microsoft Academic Graph with 250M+ works across every discipline.

About OpenAlex →

Related topics

Retrieval-augmented generation

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

Read →

LLM evaluation and benchmarks

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

Read →

Ready to track this?

Your first llm agents and tool use digest lands this week.

Start freeBrowse all topics