Jokeasy: Exploring Human-AI Collaboration in Thematic Joke Generation

2026-02-10

AI Summary

This work addresses the challenge that current conversational AI systems struggle to simultaneously support user control, authorial agency, and real-time access to external information in topical joke generation. To bridge this gap, the authors propose Jokeasy, a novel system featuring an LLM agent that dynamically assumes dual roles—“material scout” and “draft writer”—within a structured, visual canvas and a multi-stage human-AI collaboration workflow. This design seamlessly integrates live web retrieval into the humor creation process, enabling users to co-generate jokes grounded in up-to-date online content while retaining creative control. Qualitative evaluation with 18 participants, including professional comedians, demonstrates that Jokeasy effectively stimulates ideation and preserves authorial agency, while also highlighting the need for finer-grained search control and deeper integration between the visual canvas and chat interface.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Thematic jokes are central to stand-up comedy, sitcoms, and public speaking, where contexts and punchlines rely on fresh material - news, anecdotes, and cultural references that resonate with the audience. Recent advances in Large Language Models (LLMs) have enabled interactive joke generation through conversational interfaces. Although LLMs enable interactive joke generation, ordinary conversational interfaces seldom give creators enough agency, control, or timely access to such source material for constructing context and punchlines. We designed Jokeasy, a search-enabled prototype system that integrates a dual-role LLM agent acting as both a material scout and a prototype writer to support human-AI collaboration in thematic joke writing. Jokeasy provides a visual canvas in which retrieved web content is organized into editable inspiration blocks and developed through a multistage workflow. A qualitative study with 13 hobbyists and 5 expert participants (including professional comedians and HCI/AI specialists) showed that weaving real-time web material into this structured workflow enriches ideation and preserves author agency, while also revealing needs for finer search control, tighter chat-canvas integration, and more flexible visual editing. These insights refine our understanding of AI-assisted humour writing and guide future creative-writing tools.

Problem

• thematic joke generation
• human-AI collaboration
• creative agency
• real-time material access
• large language models

Innovation

• human-AI collaboration
• thematic joke generation
• dual-role LLM agent
• search-enabled creative writing
• visual inspiration canvas