# Narrative-Guided Reinforcement Learning: A Platform for Studying Language Model Influence on Decision Making

arXiv: https://arxiv.org/abs/2509.08785 · HTML: https://mlsanity.com/paper/2509.08785/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 4 of its 12 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 4 of 4)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [LLMs as Method Actors: A Model for Prompt Engineering and Architecture](https://mlsanity.com/paper/2411.05778/) (2024)

## Abstract (arXiv)

We present a preliminary experimental platform that explores how narrative elements might shape AI decision-making by combining reinforcement learning (RL) with language model reasoning. While AI systems can now both make decisions and engage in narrative reasoning, these capabilities have mostly been studied separately. Our platform attempts to bridge this gap using a dual-system architecture to examine how narrative frameworks could influence reward-based learning. The system comprises a reinforcement learning policy that suggests actions based on past experience, and a language model that processes these suggestions through different narrative frameworks to guide decisions. This setup enables initial experimentation with narrative elements while maintaining consistent environment and reward structures. We implement this architecture in a configurable gridworld environment, where agents receive both policy suggestions and information about their surroundings. The platform's modular design facilitates controlled testing of environmental complexity, narrative parameters, and the interaction between reinforcement learning and narrative-based decisions. Our logging system captures basic decision metrics, from RL policy values to language model reasoning to action selection patterns. While preliminary, this implementation provides a foundation for studying how different narrative frameworks might affect reward-based decisions and exploring potential interactions between optimization-based learning and symbolic reasoning in AI systems.