LLMPC: Large Language Model Predictive Control

Gabriel Maher
1/5/2025
cs.AIcs.CL

No official code found. Best implementation: gmaher/llmpc (10 stars, MIT, last commit 2025-03-16).

Abstract

Recent advancements in prompting techniques for Large Language Models (LLMs) have improved their reasoning, planning, and action abilities. This paper examines these prompting techniques through the lens of model predictive control (MPC). We show that LLMs act as implicit planning cost function minimizers when planning prompts are used. We propose a unified MPC framework for planning with LLMs and demonstrate improved performance over few shot prompting on several planning benchmarks.

View on arXivView PDF

Code Implementations(1)

gmaher/llmpcCommunity100%
MIT
101CSS, HTMLDec 26, 20241 years agoMIT

Similar Papers

Exploring and Benchmarking the Planning Capabilities of Large Language Models

87% match2024

Non-myopic Generation of Language Models for Reasoning and Planning

85% match1 repo162026

Test-Time Alignment for Large Language Models via Textual Model Predictive Control

84% match2025

Systematic Analysis of LLM Contributions to Planning: Solver, Verifier, Heuristic

84% match2024

Can LLMs plan paths with extra hints from solvers?

84% match2024

Detecting and Characterizing Planning in Language Models

83% match2025

Cite this paper

@article{maher2025llmpc,
  title  = {LLMPC: Large Language Model Predictive Control},
  author = {Gabriel Maher},
  year   = {2025},
  eprint = {2501.02486},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.02486v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.02486.svg)](https://codeofpaper.com/paper/2501.02486)

Discussion