# PEA: Enhancing LLM Performance on Computational-Reasoning Tasks

arXiv: https://arxiv.org/abs/2502.10938 · HTML: https://mlsanity.com/paper/2502.10938/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 16 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 7 of 7)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming](https://mlsanity.com/paper/2410.12112/) (2024)
- [Fast Analysis of the OpenAI O1-Preview Model in Solving Random K-SAT Problem: Does the LLM Solve the Problem Itself or Call an External SAT Solver?](https://mlsanity.com/paper/2409.11232/) (2024)

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

- [Programming over Thinking: Efficient and Robust Multi-Constraint Planning](https://mlsanity.com/paper/2601.09097/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have exhibited remarkable capabilities across diverse domains, prompting investigations into their potential as generic reasoning engines. While recent studies have explored inference-time computation to enhance model performance on complex problems, current research lacks a formal framework to characterize the complexity of reasoning tasks. This study introduces the Predicate-Enumeration-Aggregation (PEA) framework, a formal approach to describe and solve a class of important reasoning tasks termed computational reasoning problems. The PEA framework decomposes these problems into predicate and enumeration components, using LLMs to synthesize programs based on specified predicates, enumeration, and aggregation rules. These synthesized programs are then executed to obtain solutions to the computational tasks. We demonstrate the framework's efficacy on benchmark tasks including Boolean satisfiability problems, game of 24, and planning problems. Empirical evaluation reveals that PEA substantially enhances the performance of underlying models on benchmark computational problems, yielding an average accuracy improvement of approximately 50%, coupled with increased efficiency.