# Unlocking Structured Thinking in Language Models with Cognitive Prompting

arXiv: https://arxiv.org/abs/2410.02953 · HTML: https://mlsanity.com/paper/2410.02953/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 16 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [LongCoder: A Long-Range Pre-trained Language Model for Code Completion](https://mlsanity.com/paper/2306.14893/) (2023)
- [DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning](https://mlsanity.com/paper/2309.05173/) (2023)

## Built on by (most cited first, 8 of 8)

- [LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents](https://mlsanity.com/paper/2601.06973/) (2026)
- [Conceptual Metaphor Theory as a Prompting Paradigm for Large Language Models](https://mlsanity.com/paper/2502.01901/) (2025)
- [Engineering Systems for Data Analysis Using Interactive Structured Inductive Programming](https://mlsanity.com/paper/2503.14488/) (2025)
- [NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation Boundaries](https://mlsanity.com/paper/2606.29971/) (2026)
- [Assessing mentalization in humans and large language models](https://mlsanity.com/paper/2608.26291/) (2026)
- [Cognitive Prompts Using Guilford's Structure of Intellect Model](https://mlsanity.com/paper/2503.22036/) (2025)
- [Cognitive BASIC: An In-Model Interpreted Reasoning Language for LLMs](https://mlsanity.com/paper/2511.16837/) (2025)
- [AI Models Can Predict and Collaboratively Modulate Human Memory Search](https://mlsanity.com/paper/2608.26152/) (2026)

## Abstract (arXiv)

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern recognition. By employing systematic, step-by-step reasoning, cognitive prompting enables LLMs to tackle complex, multi-step tasks more efficiently. We introduce three variants: a deterministic sequence of cognitive operations, a self-adaptive variant in which the LLM dynamically selects the sequence of cognitive operations, and a hybrid variant that uses generated correct solutions as few-shot chain-of-thought prompts. Experiments with LLaMA, Gemma~2, and Qwen models in each two sizes on the arithmetic reasoning benchmark GSM8K demonstrate that cognitive prompting significantly improves performance compared to standard question answering.