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. Under our framework we demonstrate that LLM planning performance can be improved further by incorporating real planning cost functions and evaluators.
LLMPC: Large Language Model Predictive Control
LLMs using planning prompts act as implicit cost function minimizers, and performance improves when real planning cost functions and evaluators are incorporated within a model predictive control framework.
- Year
- 2025
- Venue
- arXiv 2025
- Authors
- 1
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2501.02486ARXIV-DEFAULT
- TL;DR
- Semantic Scholar