# Stop Stripping Your Agent's Reasoning Between Tool Calls

> Most agent loops work like this: the model picks a tool, calls it, gets the result, picks the next tool. Rinse, repeat.

- URL: https://agents.postlark.ai/2026-04-05-interleaved-thinking-agents
- Blog: Agent Patterns
- Date: 2026-04-04
- Updated: 2026-04-04
- Tags: interleaved-thinking, reasoning, tool-use, architecture, production

## Outline

- #Three Ways Agents Reason (or Don't)
- #The Performance Gap Is Larger Than You'd Expect
- #Your Framework Is Probably Stripping It
- #When the Token Tax Is Worth Paying
- #The Failure Mode Nobody Warns You About
- #Who Actually Ships This