# Heuristic Classification of Thoughts Prompting (HCoT): Integrating Expert System Heuristics for Structured Reasoning into Large Language Models

arXiv: https://arxiv.org/abs/2604.12390 · HTML: https://mlsanity.com/paper/2604.12390/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 14 of its 38 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 14 of 14)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [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)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Evaluating the Performance of Large Language Models on GAOKAO Benchmark](https://mlsanity.com/paper/2305.12474/) (2023)
- [Hypothesis Search: Inductive Reasoning with Language Models](https://mlsanity.com/paper/2309.05660/) (2023)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations](https://mlsanity.com/paper/2305.18354/) (2023)
- [Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges](https://mlsanity.com/paper/2409.02387/) (2024)

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

- [From Explicit Elements to Implicit Intent: A Predefined Library for Auditable Behavioral Inference](https://mlsanity.com/paper/2606.11207/) (2026)

## Abstract (arXiv)

This paper addresses two limitations of large language models (LLMs) in solving complex problems: (1) their reasoning processes exhibit Bayesian-like stochastic generation, where each token is sampled from a context-dependent probability distribution, leading to inherently random decision trajectories rather than deterministic planning; (2) the reasoning and decision-making mechanisms are statically decoupled, meaning dynamically retrieved domain knowledge fails to dynamically adjust the underlying reasoning strategy. These dual deficiencies result in initial decisions lacking strategic anchoring and reasoning chains often failing to converge on correct solutions, as stochastic generation lacks mechanisms for trajectory correction or knowledge-guided optimization during sequential reasoning. To resolve these issues, we propose a problem-solving method integrated into the LLM's generation process to guide reasoning. This method, compatible with numerous LLMs and featuring reusable solutions, is grounded in a novel Heuristic-Classification-of-Thoughts prompting schema (HCoT). HCoT synergizes the LLM's reasoning ability with a structured problem space via a heuristic classification model that controls the reasoning process and provides reusable abstract solutions. Evaluated on two complex inductive reasoning tasks with ill-defined search spaces, HCoT outperforms existing approaches (e.g., Tree-of-Thoughts and Chain-of-Thoughts prompting) in performance. On the well-structured 24 Game task, HCoT demonstrates significantly higher token efficiency compared to the state-of-the-art Tree-of-Thoughts-Breadth-First-Search. In terms of both accuracy and token usage, HCoT achieves a Pareto frontier balance, offering a strong trade-off between performance and computational cost.