MetaCrit: A Critical Thinking Framework for Self-Regulated LLM Reasoning
This addresses the issue of unreliable reasoning in LLMs for applications requiring critical thinking, such as analytical writing, though it is incremental as it builds on existing metacognitive theory.
The paper tackles the problem of LLMs failing on multi-hop questions with counterfactual premises and being vulnerable to adversarial prompts by proposing MetaCrit, a multi-agent framework for self-regulated reasoning, which significantly improves content truthfulness and logical soundness while eliminating toxic outputs across multiple benchmarks and model backbones.
Large language models (LLMs) fail on over one-third of multi-hop questions with counterfactual premises and remain vulnerable to adversarial prompts that trigger biased or factually incorrect responses, which exposes a fundamental deficit in self-regulated reasoning. We propose \textbf{MetaCrit}, a multi-agent framework grounded in Nelson and Narens' metacognitive regulation theory. MetaCrit decomposes reasoning regulation into four agents: object-level generation, a \emph{monitoring} agent that assesses response validity, a \emph{control} agent that critiques logical soundness, and a meta-level synthesizer that integrates all signals into a final response. Evaluation across eight benchmarks, four model backbones, and a college-level analytical writing study shows that MetaCrit significantly improves content truthfulness and logical soundness while eliminating toxic outputs. Its modular design allows individual agents to be integrated into existing frameworks as drop-in components without architectural modifications.