Tool Recommendation for Multi-Step Agents
Finding every tool a task needs
A multi-step agent task fails when a single tool it needs is missing, yet the tools an agent may need are too many to list. This research paper shows how Arcade gives an agent all of them through a fixed interface of three tools, and what it does to accuracy and cost.
What's in the paper
-
How three tools reach a catalog of 8,200
-
57% more complete tool chains than BM25
-
Up to 40% lower input tokens and cost
-
When a static tool list is still cheaper
Trusted in prod by
You might also like
About Arcade
Arcade is the action runtime for enterprise AI agents. We enforce your security and governance policies on every action, execute reliably across every business system, and govern your agents from a single control plane. Configure once and use any model, framework, and client. Deploy the first agent the same way you deploy the hundredth.
Additional resources
