---
title: "The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning"
authors:
  - "Sheila Schoepp"
  - "Masoud Jafaripour"
  - "Yingyue Cao"
  - "Tianpei Yang"
  - "Fatemeh Abdollahi"
  - "Shadan Golestan"
  - "Zahin Sufiyan"
  - "Osmar R. Zaiane"
  - "Matthew E. Taylor"
doi: "10.24963/ijcai.2025/1181"
url: "https://ijcai.org/proceedings/2025/1181"
pdf: "https://ijcai.org/proceedings/2025/1181.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "10641-10649"
track: "Survey Track"
keywords:
  - "Machine Learning: ML: Reinforcement learning"
  - "Natural Language Processing: NLP: Language models"
---

# The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning

Sheila Schoepp, Masoud Jafaripour, Yingyue Cao, Tianpei Yang, Fatemeh Abdollahi, Shadan Golestan, Zahin Sufiyan, Osmar R. Zaiane, Matthew E. Taylor

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 10641-10649. DOI: [10.24963/ijcai.2025/1181](https://doi.org/10.24963/ijcai.2025/1181)

## Abstract

Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Large Language Models (LLMs) and Vision-Language Models (VLMs) have recently emerged, exhibiting impressive capabilities in multimodal understanding and reasoning. These advances have led to a surge of research integrating LLMs and VLMs into RL. This survey reviews representative works in which LLMs and VLMs are used to overcome key challenges in RL, such as lack of prior knowledge, long-horizon planning, and reward design. We present a taxonomy that categorizes these LLM/VLM-assisted RL approaches into three roles: agent, planner, and reward. We conclude by exploring open problems, including grounding, bias mitigation, improved representations, and action advice. By consolidating existing research and identifying future directions, this survey establishes a framework for integrating LLMs and VLMs into RL, advancing approaches that unify natural language and visual understanding with sequential decision-making.