---
title: "Grounding Open-Domain Knowledge from LLMs to Real-World Reinforcement Learning Tasks: A Survey"
authors:
  - "Haiyan Yin"
  - "Hangwei Qian"
  - "Yaxin Shi"
  - "Ivor Tsang"
  - "Yew-Soon Ong"
doi: "10.24963/ijcai.2025/1198"
url: "https://ijcai.org/proceedings/2025/1198"
pdf: "https://ijcai.org/proceedings/2025/1198.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "10797-10806"
track: "Survey Track"
keywords:
  - "Natural Language Processing: NLP: Applications"
  - "Machine Learning: ML: Reinforcement learning"
  - "Natural Language Processing: NLP: Language models"
---

# Grounding Open-Domain Knowledge from LLMs to Real-World Reinforcement Learning Tasks: A Survey

Haiyan Yin, Hangwei Qian, Yaxin Shi, Ivor Tsang, Yew-Soon Ong

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 10797-10806. DOI: [10.24963/ijcai.2025/1198](https://doi.org/10.24963/ijcai.2025/1198)

## Abstract

Grounding open-domain knowledge from large language models (LLMs) into real-world reinforcement learning (RL) tasks represents a transformative frontier in developing intelligent agents capable of advanced reasoning, adaptive planning, and robust decision-making in dynamic environments. In this paper, we introduce the LLM-RL Grounding Taxonomy, a systematic framework that categorizes emerging methods for integrating LLMs into RL systems by bridging their open-domain knowledge and reasoning capabilities with the task-specific dynamics, constraints, and objectives inherent to real-world RL environments. This taxonomy encompasses both training-free approaches, which leverage the zero-shot and few-shot generalization capabilities of LLMs without fine-tuning, and fine-tuning paradigms that adapt LLMs to environment-specific tasks for improved performance. We critically analyze these methodologies, highlight practical examples of effective knowledge grounding, and examine the challenges of alignment, generalization, and real-world deployment. Our work not only illustrates the potential of LLM-RL agents for enhanced decision-making, but also offers actionable insights for advancing the design of next-generation RL systems that integrate open-domain knowledge with adaptive learning.