Wavelength.AI: Extending the Collaborative Game Wavelength as a Testbed for Studying Shared Understanding in Human–Agent Collaboration

Morrison, Katelyn; Gonzalez, Gabriel Enrique; Ashktorab, Zahra; Riemer, Matt; Anderson, Andrew; Bouneffouf, Djallel; Weisz, Justin D.

doi:10.24963/ijcai.2026/981

Wavelength.AI: Extending the Collaborative Game Wavelength as a Testbed for Studying Shared Understanding in Human–Agent Collaboration

Katelyn Morrison, Gabriel Enrique Gonzalez, Zahra Ashktorab, Matt Riemer, Andrew Anderson, Djallel Bouneffouf, Justin D. Weisz

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Demo Track. Pages 8466-8470.

https://doi.org/10.24963/ijcai.2026/981

Keywords

AI: Agent-based and Multi-agent Systems
AI: Humans and AI

Abstract

AI's increasing role as a personal agent assisting knowledge workers in everyday tasks underscores the need to investigate how to help human–agent teams build a shared understanding. We extend the collaborative "mind-reading" game Wavelength to include an AI teammate, presenting the first demonstration of an LLM capable of playing this game. Based on our agent–agent play experiments, we developed Wavelength.AI, which implements two strategies to support shared understanding: an initial team grounding conversation and post-game reflective explanations. We interpret higher team scores as evidence for better shared understanding in a preliminary user study with 24 human–AI teams. Our findings reveal that Wavelength.AI can help researchers evaluate and design different strategies to shape human-agent teams' shared understanding. Human players can see if they are on the same wavelength with AI and view our demo video today at https://play-wavelength-ai.com.

Katelyn Morrison, Gabriel Enrique Gonzalez, Zahra Ashktorab, Matt Riemer, Andrew Anderson, Djallel Bouneffouf, and Justin D. Weisz. 2026. Wavelength.AI: Extending the Collaborative Game Wavelength as a Testbed for Studying Shared Understanding in Human–Agent Collaboration. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8466–8470. https://doi.org/10.24963/ijcai.2026/981

@inproceedings{ijcai2026p981,
  title     = {Wavelength.AI: Extending the Collaborative Game Wavelength as a Testbed for Studying Shared Understanding in Human–Agent Collaboration},
  author    = {Morrison, Katelyn and Gonzalez, Gabriel Enrique and Ashktorab, Zahra and Riemer, Matt and Anderson, Andrew and Bouneffouf, Djallel and Weisz, Justin D.},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {8466--8470},
  year      = {2026},
  month     = {8},
  note      = {Demo Track},
  doi       = {10.24963/ijcai.2026/981},
  url       = {https://doi.org/10.24963/ijcai.2026/981},
}

TY  - CPAPER
TI  - Wavelength.AI: Extending the Collaborative Game Wavelength as a Testbed for Studying Shared Understanding in Human–Agent Collaboration
AU  - Morrison, Katelyn
AU  - Gonzalez, Gabriel Enrique
AU  - Ashktorab, Zahra
AU  - Riemer, Matt
AU  - Anderson, Andrew
AU  - Bouneffouf, Djallel
AU  - Weisz, Justin D.
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 8466
EP  - 8470
DO  - 10.24963/ijcai.2026/981
UR  - https://doi.org/10.24963/ijcai.2026/981
ER  -