HomeResearch LibraryCRITIC: Large Language Models Can Self-Correct with Too…
system architectureChapter 5ICLR 2024 · 2023

CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

Zhibin Gou (Tsinghua), Zhihong Shao (Tsinghua)

Abstract

We present CRITIC, a framework that allows LLMs to validate and progressively amend their own outputs with the assistance of external tools. CRITIC uses tool feedback to identify and correct errors.

Eigenvector Insight — Zone III / PASF-PADE AnalysisNot part of the original paper
Eigenvector Research — Marco van Hurne
How this paper contributes to solving the Zone III problem (PASF-PADE)

CRITIC shows that external tool verification can dramatically improve agent output quality. For enterprise agents, this means integrating domain-specific validators (schema checkers, business rule engines) into the correction loop.

Why AI is not sufficient for Zone III without this

Zone III refers to high-complexity, high-risk, long-running agentic workflows — the class of enterprise AI deployments where a single failure can cascade across hundreds of steps. Standard AI models, trained to predict the next token, are not inherently designed for durable, governed, multi-step execution. This paper addresses one or more of the structural gaps that make Zone III deployments unsafe without explicit architectural intervention.

Key Contributions

  • →Tool-interactive self-correction
  • →Progressive error amendment
  • →External verification integration

Topics

self-correctiontool-interactive critiquingerror correctionverification