Wordplay: When Language Meets Games @ EMNLP 2025


Your one stop shop for all things interactive narrative + AI!

Back to the '80s

Overview



Date and time: November 9th, 2025 - 09:00 to 17:00 (China Standard Time)
Location: Suzhou, China
Shared task: Official website
Submission website: OpenReview
This workshop focused on exploring the utility of interactive narratives, think everything from classic text-adventures like Zork to modern Twine games, to fill a role as the learning environments of choice for language-based tasks including but not limited to storytelling. A few previous iterations of this workshop took place very successfully with hundreds of attendees, at NeurIPS 2018, NeurIPS 2020, NAACL 2022, and ACL 2024. Since then, the community of people working in this area has rapidly increased. This workshop aims to be a centralized place where all researchers involved across a breadth of fields can interact and learn from each other. Furthermore, it will act as a showcase to the wider NLP/RL/Game communities on interactive narrative’s place as a learning environment. The program will feature a collection of invited talks in addition to contributed talks and posters from each of these sections of the interactive narrative community and the wider NLP and RL communities.

We like all things:

  • Interactive narrative: game playing RL agents, game generation, etc.
  • Interactive language learning
  • Natural language generation
  • Improvisational storytelling
  • And more! Anything you can think of that involves narrative, interactivity, and language!


    Check out the full version of our overview!

Schedule - Sunday, November 9th (China Time)


08:55 – 09:00

Opening Remarks

Pacific Time 16:55 – 17:00 (Nov 8)

09:00 – 09:45

Using generative AI to transform narrative design in games

-Sudha Rao-

Pacific Time 17:00 – 17:45 (Nov 8)

In our team at Microsoft Research, we have been exploring how generative AI can transform narrative design games. In the first part of the talk, I will introduce GENEVA, a prototype tool for generating and visualizing branching narratives using large language models (LLMs). This tool allows narrative designers to develop and iterate narratives much faster than traditional tools. In the second part, I will present a case study on how generative AI can evolve game narratives in real-time based on player feedback. The goal of this work is to understand how players, game creators and generative AI can collaboratively create and evolve a game’s narrative over time. Learn more about our team’s work on our website – https://msr-emergence.com/.

09:45 – 10:30

Building AI Agents that Reason and Act Like Humans

-Xin (Eric) Wang-

Pacific Time 17:45 – 18:30 (Nov 8)

10:30 – 11:00

Coffee Break (30 minutes)

Pacific Time 18:30 – 19:00 (Nov 8)

11:00 – 11:45

Beyond Exams: Evaluating LLM Agents Through Interactive Collaboration and Competition

-Diyi Yang-

Pacific Time 19:00 – 19:45 (Nov 8)

11:45 – 12:00

Lightning Talks - Outstanding Papers

Pacific Time 19:45 – 20:00 (Nov 8)

12:00 – 13:15

Lunch Break and Posters (75 minutes)

Pacific Time 20:00 – 21:15 (Nov 8)

13:15 – 13:45

Lightning Talks - Spotlight Papers

Pacific Time 21:15 – 21:45 (Nov 8)

13:45 – 14:45

Common-sense Persona-Grounded Dialogue Challenge (CPDC) 2025

Pacific Time 21:45 – 22:45 (Nov 8)

14:45 – 15:30

Causality and Intention: What narrative understanding teaches us about AGI

-Boyang Li-

Pacific Time 22:45 – 23:30 (Nov 8)

15:30 – 16:00

Coffee Break (30 minutes)

Pacific Time 23:30 – midnight (Nov 8)

16:00 – 16:45

LLM Agents for In-the-Wild Video Game-Playing

-Jaewoo Ahn-

Pacific Time 00:00 – 00:45

Recent advancements in Large Language Models (LLMs) have showcased their impressive capabilities in various language tasks. However, traditional evaluation methods often fall short in capturing the full spectrum of LLMs’ abilities, particularly in interactive and dynamic contexts. This talk explores the limitations of conventional benchmarks and proposes a shift towards evaluating LLM agents through interactive collaboration and competition. By engaging LLMs in multi-agent environments, we can better assess their adaptability, problem-solving skills, and social intelligence. This approach not only provides a more comprehensive understanding of LLM capabilities but also paves the way for developing more robust and versatile AI systems.

16:45 – 17:00

Closing Remarks

Pacific Time 00:45 – 01:00

Speakers


Diyi Yang

Diyi Yang

Stanford University

Sudha Rao

Sudha Rao

Microsoft

Xin Wang

Xin Wang

University of California Santa Barbara (UCSB) & Simular

Boyang Li

Boyang Li

Nanyang Technological University (NTU)

Jaewoo Ahn

Jaewoo Ahn

Seoul National University (SNU)

Accepted Papers


Outstanding Papers

Spotlight Papers

Poster Papers

Shared Task



Shared task: Common-sense Persona-Grounded Dialogue Challenge (CPDC) 2025

Reviewers


  • Anchao Li (ByteDance)
  • Arya Honraopatil (University of Maryland, Baltimore County)
  • Ashutosh Adhikari (University of Edinburgh)
  • Christopher Zhang Cui (University of California, San Diego)
  • Hosein Rezaei (University of York)
  • Kuan Lu (Cornell University)
  • Marcus McAllister (University of Maryland, Baltimore County)
  • Mete Ismayilzada (Swiss Federal Technology Institute of Lausanne)
  • Nischal Reddy Chandra (Adobe)
  • Patricia J Delafuente (University of Maryland, Baltimore County)
  • Samuel Barry (Mistral AI)
  • Shadab Hafiz Choudhury (University of Maryland, Baltimore County)
  • Silin Gao (Swiss Federal Technology Institute of Lausanne)

Organizers


University of California, San Diego (UCSD) & Nvidia

École Polytechnique Fédérale de Lausanne (EPFL)

Microsoft Research

University of Maryland, Baltimore County (UMBC)

Sony Group Corporation

University of California, San Diego (UCSD)

Central University of Finance and Economics

Microsoft Research

Our Sponsors



We are grateful to our sponsors for their generous support of Wordplay 2025. Their commitment helps make this workshop possible and supports the advancement of research in language-based interactive environments.

Microsoft

Register now to join the Microsoft Research Forum
Join us for a continuous exchange of ideas about science and technology research in the era of general AI. This series explores recent research advances, bold new ideas, and important discussions with the research community.


Sony

We gratefully thank Sony for their support in organizing the Wordplay workshop, especially in organizing the CPDC challenge!


Interested in Sponsoring?
If you’re interested in sponsoring the Wordplay Workshop, please contact us at wordplay.workshop.organizers@gmail.com for more information about sponsorship opportunities.