LLM-Guided Reinforcement Learning for Interactive Environments

Fuxue Yang, Jiawen Liu and Kan Li ()
Additional contact information
Fuxue Yang: School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100081, China
Jiawen Liu: School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100081, China
Kan Li: School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100081, China

Mathematics, 2025, vol. 13, issue 12, 1-13

Abstract: We propose herein LLM-Guided Reinforcement Learning (LGRL) , a novel framework that leverages large language models (LLMs) to decompose high-level objectives into a sequence of manageable subgoals in interactive environments. Our approach decouples high-level planning from low-level action execution by dynamically generating context-aware subgoals that guide the reinforcement learning (RL) agent. During training, intermediate subgoals—each associated with partial rewards—are generated based on the agent’s current progress, providing fine-grained feedback that facilitates structured exploration and accelerates convergence. At inference, a chain-of-thought strategy is employed, enabling the LLM to adaptively update subgoals in response to evolving environmental states. Although demonstrated on a representative interactive setting, our method is generalizable to a wide range of complex, goal-oriented tasks. Experimental results show that LGRL achieves higher success rates, improved efficiency, and faster convergence compared to baseline approaches.

Keywords: reinforcement learning; large language models; chain of thought (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/12/1932/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/12/1932/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:12:p:1932-:d:1675892

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().