Large Action Models (LAMs)
Use a model class specifically trained for action execution (tool calls, UI navigation, workflow steps) rather than text generation, when the workload is dominated by reliably completing actions in real systems.
Problem
Text-tuned LLMs are suboptimal for action-completion workloads: they generate plausible-sounding tool calls with wrong arguments, hallucinate UI steps, fail on long action chains. The mismatch between training objective (next-token) and operational objective (action committed) shows up as unreliable execution that no amount of prompting fully fixes.
Solution
Identify workloads where success is measured by action completion (UI automation, multi-step API orchestration, structured workflow). Route those workloads to a LAM (Microsoft's research, Apple's UI-Tars, etc.) rather than a general LLM. Keep text-tuned LLMs for generation workloads. Pair with multi-model-routing, complexity-based-routing, computer-use, agent-computer-interface.
When to use
- Workload success measured by action completion not text quality.
- Long action chains where text-LLM-driven scaffolding is unreliable.
- LAM availability for the target environment (UI, API).
Open the full interactive page →
Diagram, neighbourhood map, code examples, related patterns and full provenance.