# MetaCrit: A Critical Thinking Framework for Self-Regulated LLM Reasoning

arXiv: https://arxiv.org/abs/2507.15015 · HTML: https://mlsanity.com/paper/2507.15015/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 11 of its 37 references that are in the map.
- First posted on arXiv 20 Jul 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 11 of 11)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023)
- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](https://mlsanity.com/paper/2310.06117/) (2023)
- [ExpertPrompting: Instructing Large Language Models to be Distinguished Experts](https://mlsanity.com/paper/2305.14688/) (2023)
- [Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge](https://mlsanity.com/paper/2504.07887/) (2025)
- [ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection](https://mlsanity.com/paper/2505.16475/) (2025)
- [Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoning](https://mlsanity.com/paper/2506.15732/) (2025)

## Built on by (most cited first, 1 of 1)

- [Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation](https://mlsanity.com/paper/2509.20553/) (2025)

## Abstract (arXiv)

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 MetaCrit, a multi-agent framework grounded in Nelson and Narens' metacognitive regulation theory. MetaCrit decomposes reasoning regulation into four agents: object-level generation, a monitoring agent that assesses response validity, a 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.