Tool-Augmented Self-Correction
After drafting, the model uses external tools (search, code execution, calculator) to verify its own claims — grounded self-correction, not more confident hallucination.
Intent & Description
🎯 Intent
Ground the self-correction loop in external reality, not just the model’s own beliefs.
📋 Context
Your agent generates drafts with factual claims (verifiable by search), code (runnable), or arithmetic (calculable). After drafting, the model self-critiques — but the critique is just another model call with no external grounding. It reinforces the same errors it made the first time.
💡 Solution
After draft generation, the model emits a critique that names suspected errors and issues tool calls to verify them. Tool results inform the revised output. Iterate until tools find no more issues or the budget exhausts.
Real-world Use Case
- The model has external tools (search, code, calculator) that can provide grounded ground-truth signals.
- Ungrounded self-critique recycles the model’s blind spots and fails to catch real errors.
- Iteration to convergence (or a budget cap) is acceptable in the latency model.
Source
📌 TL;DR
Self-critique + tool calls = grounded correction. Search to verify facts, run code to check logic, use a calculator for math. Don’t let the model just convince itself it’s right.
Advantages
- Grounded self-correction beats ungrounded reflection — tools provide external reality checks.
- Tool invocations during critique are auditable and replayable.
Disadvantages
- Latency and cost per turn — tool calls add up.
- Tool selection during critique is itself a reasoning problem the model can get wrong.