mlsanityData to 7 Oct 2026

Dialogue Shaping: Empowering Agents through NPC Interaction

arXiv 2307.15833 ↗First posted 28 Jul 2023cs.CLcited by 8

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

One major challenge in reinforcement learning (RL) is the large amount of steps for the RL agent needs to converge in the training process and learn the optimal policy, especially in text-based game environments where the action space is extensive. However, non-player characters (NPCs) sometimes hold some key information about the game, which can potentially help to train RL agents faster. Thus, this paper explores how to interact and converse with NPC agents to get the key information using large language models (LLMs), as well as incorporate this information to speed up RL agent's training using knowledge graphs (KGs) and Story Shaping.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 10 of its 11 references that are in the map. First posted on arXiv 28 Jul 2023.

Builds on

10 of 11 references.

References · 10

  1. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  2. 2019Learning to Speak and Act in a Fantasy Text Adventure Gamecited by 122
  3. 2020Keep CALM and Explore: Language Models for Action Generation in Text-based Gamescited by 108
  4. 2020Graph Constrained Reinforcement Learning for Natural Language Action Spacescited by 80
  5. 2018Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learningcited by 53
  6. 2020How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worldscited by 38
  7. 2020Bringing Stories Alive: Generating Interactive Fiction Worldscited by 28
  8. 2020Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Gamescited by 22
  9. 2021Inherently Explainable Reinforcement Learning in Natural Languagecited by 16
  10. 2023Story Shaping: Teaching Agents Human-like Behavior with Storiescited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 4; 2025: 3.

8 papers.

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  2. 2024Teaching Large Language Models to Reason with Reinforcement Learningcited by 158
  3. 2025Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Modelscited by 48
  4. 2024Player-Driven Emergence in LLM-Driven Game Narrativecited by 16
  5. 2024Unbounded: A Generative Infinite Game of Character Life Simulationcited by 14
  6. 2024Branching Narratives: Character Decision Points Detectioncited by 1
  7. 2025Integrating Machine Learning into Belief-Desire-Intention Agents: Current Advances and Open Challengescited by 1
  8. 2025Symbolically Scaffolded Play: Designing Role-Sensitive Prompts for Generative NPC Dialoguecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games
  2. 2024STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models
  3. 2022A Mixture-of-Expert Approach to RL-based Dialogue Management
  4. 2024Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations
  5. 2025Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning
  6. 2026First Make It Playable, Then Make It Good: Staged Interaction Learning for Small Dialogue-Game Agents
  7. 2025PARL: Prompt-based Agents for Reinforcement Learning
  8. 2024Large Language Models as Agents in Two-Player Games