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.
Yao‐Wen Sang (Wed,) studied this question.