Why did the AI agent cross the road?

tdonnel — Mon, 08 Jun 2026 18:31:17 +0000

Why did the AI agent cross the road? tdonnel Mon, 06/08/2026 - 14:31

Workshopping, an iterative process where creators share ideas, test what works, and refine what doesn’t through collective feedback, is at the heart of any writers’ group. This collaborative dynamic inspired 91�� PhD students Shiwei Hong to explore whether artificial intelligence (AI) could benefit from a similar approach.

Hong developed a novel multi-agent system that simulates a collaborative comedy writing environment in which AI agents generate, critique, and refine humorous content together. Her research, recently accepted to the prestigious 64th Annual Meeting of the Association for Computational Linguistics, investigates how structured interaction among AI agents can improve creative output.

Shiwei Hong. Photo provided.

Humor remains challenging for artificial intelligence. “Generating a joke or something that is very funny is actually a very tricky question, because it requires a lot of how humans interpret the generated piece,” said Hong, who is working on a degree in computer science.

She created a “sandbox” environment to mirror real-world creative collaboration, populated by 35 AI agents assigned distinct roles and personalities powered by GPT-4.

“Five agents acted as performers. The rest acted as critics or audience members,” said Hong.

Designing 35 unique agent personas required imagination as well as technical expertise. Drawing on her interest in writing fiction, Hong created characters with varied social and cultural backgrounds, adding depth to the simulated interactions.

In one experimental environment, the performer agents generated two scripts in sequence without feedback; in another, they engaged the audience members in critique and discussion between the rounds of generation. The difference was significant.

Human evaluators compared outputs across multiple criteria, such as humor, coherence, and social tone. In more than 70 percent of cases, evaluators preferred scripts produced in the second round of the discussion-based environment.

The improvement appears to stem from collective learning. As agents interact, they build on shared insights, identifying patterns in audience preferences and refining their outputs accordingly. Technically, this process is supported by a shared conversational memory stored in a vector database, allowing agents to retrieve relevant past exchanges and incorporate them into new content. The result is an iterative, emergent form of creativity that begins to resemble human collaboration.

Looking ahead, Hong and her advisor, Assistant Professor Zhicong Lu, aim to expand the system by incorporating human participants and richer modes of interaction. Future directions include integrating voice, gestures, and immersive technologies such as virtual and augmented reality to better capture the nuances of live performance.

“In real comedy, we have faces, gestures, and real voices,” she said. “We hope to bring more of that into the system.”

By demonstrating that workshopping can significantly enhance machine-generated humor, Hong’s work suggests the future of artificial intelligence may lie not only in more advanced individual models, but also in communities of agents learning, creating, and perhaps even laughing together.

This week in AI

CIO Charmaine Madison honored with Change Champion Award

Charmaine Madison, vice president for information technology and chief information officer, has been honored by Cloudforce with a Change Champion Award for leading transformative change at George Mason in the realm of AI, inspiring teams, and challenging the status quo to adopt new ways of working.

Learn how Madison champions the adoption of generative AI across the university.

Explore Research at George Mason

Topics

Human Computer Interaction

computer science

College of Engineering and Computing

Artificial Intelligence

doctoral students

Research

Researching the effect of smartphone-free schools in Virginia

Martha Bushong — Tue, 08 Oct 2024 22:05:15 +0000

Researching the effect of smartphone-free schools in Virginia Martha Bushong Tue, 10/08/2024 - 18:05

Virginia K-12 students who returned to school this fall may be confronted with smartphone-free hallways and classrooms as part of new state cellphone bans that are sweeping the United States. Nora McDonald, an assistant professor in the Department of Information Sciences and Technology (IST) at 91��, is teaming up with the Prince William County School district to try to understand how students, teachers, administrators, and parents are reacting to these bans and what are the long-term implications.

Photo by iStock

Increasing concerns about the use of personal internet-connected (“smart”) phones and other devices among youth have dramatically intensified, especially about the constant connectivity in school settings. Scholars, educators, and lawmakers are taking action to combat the distractions, cyberbullying, and reduced face-to-face social interaction they perceive to be created and exacerbated by smart devices with near or total schoolwide bans.

McDonald says, “It is urgent that we do this work … we know that youth use technology to seek support for social and identity development, particularly for certain identities. At the same time, we do not understand how near-constant use of smartphones might simultaneously be eroding or limiting outlets for social support-seeking and identity expression offline.”

While individual schools have already responded with cellphone bans, Virginia is among those states that will be introducing a full K through 12 ban starting this fall, though not all may adopt them until 2025. The goal of this proposed research is to talk to teachers, administrators, parents, and students before and after the imposition of cell phone bans creating a critical opportunity to determine what primarily psychosocial outcomes may be observed and whether any are sustained, or even potentially amplified over time.

Through focus group interviews and qualitative surveys, McDonald is now working on engaging parents and students to learn more about these cellphone bans' impact on student behaviors and social experiences in and out of the classroom, specifically how it impacts how students spend their time and where they are seeking social support.

Her work builds on research in her field of human–computer interaction (HCI) that has focused on the benefits of social media for marginalized identities but increasingly acknowledges the darker side of these privacy-invasive algorithms on youth's sense of self. She published a paper at CHI 2024 and in The Conversation on teen self-perceptions and digital literacy in relationship to social media “for you” algorithms. Ultimately, McDonald says, she wants to “engage youth awareness to understand why they are seeing the toxic content or the misinformation they are seeing, and the privacy-invasive algorithms behind it.”

This month, McDonald attended the Symposium on Child Safety Research and Policy hosted by the Center of Democracy and Technology to talk more about these pressing issues related to social media technology and youth.