AutoCrit: A Meta-Reasoning Framework for Self-Critique and Iterative Error Correction in LLMChains-of-Thought

Read the full article See related articles

Discuss this preprint

Start a discussion What are Sciety discussions?

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

Large Language Models (LLMs) have shown im- pressive reasoning abilities with the use of chain-of-thought (CoT) prompting. However, reasoning is still brittle: small errors early on propagate forward to lead to confidently asserted but erroneous conclusions. This paper presents AutoCrit, a meta- reasoning system that incorporates structured self-criticism and iterative error-fixing directly into the CoT procedure. AutoCrit integrates a reasoning agent, a critique agent, and an execution monitor in an active feedback loop to detect and correct in- consistency proactively step by step. On mathematical reasoning benchmarks (GSM8K), commonsense inference (CSQA2), and interactive planning (ALFWorld) benchmarks, AutoCrit achieves accuracy improvements of 12–18% over baseline CoT and reduces error propagation rates by half. Theoretical analysis of AutoCrit as an iterative fixed-point system formally establishes it rigorously and provides error-propagation limits that demon- strate its scalability. This work advances LLM reliability by showing that incorporating critique into reasoning outperforms post-hoc validation, the foundation for future reasoning-intensive applications in AI-assisted decision-making.

Article activity feed