8 Types of LLMs Used in AI Agents, From GPT and MoE to LAM and LCM
mdancho84 · x · 2026-10-09
A primer on 8 model types used in AI agents: GPT (general text backbone), MoE (token routing to experts for efficient scaling), LRM (multi-step reasoning, RAG/tool use), VLM (image+text perception), SLM (edge/low-latency), LAM (planning and acting via tools/APIs/robots), HLM (layered user/item/task submodels for complex workflows), and LCM (mapping words to higher-level concepts for semantic abstraction).
Related event: A guide to the 8 types of LLMs used in AI agents(4 posts)→
More from coding & agent
- Manning publishes 'Building LLM Applications with DSPy' on systematic LLM development — lateinteraction · 2026-10-10
- YC partner shares multi-agent workflow: agents write briefs for each other like middle managers — ycombinator · 2026-10-10
- AI writing skill boosts output to 4 posts a week, human editors become the bottleneck — danshipper · 2026-10-10
- AI agent digs through Azure billing to recover nearly $2,000 in lost credits — pswider · 2026-10-10
- HQ Agent Tool Ships Major Update: Per-App Postgres, Full-Stack Next.js, Interactive Pages — jacob_posel · 2026-10-10
- Agent swarm converts GTA footage to 3D scenes in just a few hours — Daniel_Farinax · 2026-10-10