Selected work

Representative Papers

Elsewise: Authoring AI-Based Interactive Narrative with Possibility Space Visualization

Dec 21, 2025arXiv.org

Interactive narrative (IN) authors craft spaces of divergent narrative possibilities for players to explore, with the player's input determining which narrative possibilities they actually experience. Generative AI can enable new forms of IN by improvisationally expanding on pre-authored content in response to open-ended player input. However, this extrapolation risks widening the gap between author-envisioned and player-experienced stories, potentially limiting the strength of plot progression and the communication of the author's narrative intent. To bridge the gap, we introduce Elsewise: an authoring tool for AI-based INs that implements a novel Bundled Storyline concept to enhance author's perception and understanding of the narrative possibility space, allowing authors to explore similarities and differences between possible playthroughs of their IN in terms of open-ended, user-configurable narrative dimensions. A user study (n=12) shows that our approach improves author anticipation of player-experienced narrative, leading to more effective control and exploration of the narrative possibility spaces.

2 citationsRead paper

Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value

Dec 03, 2025

This paper addresses governance risks arising from misalignment between AI systems and societal institutions’ or individuals’ values. To tackle this, it proposes a “full-stack alignment” framework centered on a novel “thick value model” that distinguishes enduring values from context-sensitive preferences, thereby enabling normative reasoning, modeling of collective goods, and cross-level value embedding. Methodologically, the framework integrates value-sensitive decision architectures, socially embedded agent design, value-aware institutional and economic mechanisms, and is empirically validated across five domains: AI governance, normative agent construction, win-win negotiation, meaning-preserving incentive design, and democratic oversight institutions. Results demonstrate that the framework systematically enhances value consistency between AI development and societal well-being. It offers a theoretically grounded yet practically viable alignment paradigm for trustworthy AI—bridging normative theory, institutional design, and technical implementation.

1 citationsRead paper

IRIS: Navigating and Reflecting on Writing Traces Using Intelligent Document Histories

Aug 19, 2026

本文通过智能文档历史记录技术，使写作过程痕迹可视化和可交互，帮助作者理解其写作进程。方法包括修订高亮、概念过滤器及自然语言查询。

0 citationsRead paper

TailVis: Expressive Chart Refinement Preserving Data-Binding Integrity

Jul 28, 2026

This work addresses the limitations of existing data visualization tools, which often fail to support fine-grained visual customization while preserving data binding, thereby forcing users to resort to external graphic editors. To bridge this gap, we present TailVis, a system that extends the InfoVis reference model to encompass a post-rendering design phase. TailVis integrates element-level direct selection, natural language input, and dynamic GUI controls, augmented by referential interactions that enable data-aware, open-ended editing. The system maintains data-binding integrity through a dedicated preservation mechanism, employs an extensible selection model, and supports iterative design via provenance-aware history management. User studies demonstrate that TailVis significantly reduces repetitive operations and effectively enables expressive, data-consistent chart refinement within a unified environment.

0 citationsRead paper

"When to Hand Off, When to Work Together": Expanding Human-Agent Co-Creative Collaboration through Concurrent Interaction

Mar 02, 2026

This work addresses the challenge that current AI agents struggle to interpret users’ concurrent interaction intents on shared artifacts, thereby limiting dynamic co-creation. To overcome this, we propose CLEO—a collaborative intelligent agent grounded in mixed-initiative interaction principles—that dynamically switches among delegation, guidance, and collaboration modes by recognizing user concurrent behaviors in real time. We introduce the first collaborative model capable of real-time intent interpretation, identifying five behavioral patterns, six triggering mechanisms, and four enabling factors, and implement a decision framework comprising six interactive loops. Based on 214 rounds of interactions with professional designers, we quantitatively analyze mode usage (70.1% delegation, 28.5% guidance, 31.8% collaboration) and release design guidelines alongside a labeled dataset to support future research.

0 citationsRead paper

Recent publications

Latest Papers

IRIS: Navigating and Reflecting on Writing Traces Using Intelligent Document Histories

Aug 19, 2026

本文通过智能文档历史记录技术，使写作过程痕迹可视化和可交互，帮助作者理解其写作进程。方法包括修订高亮、概念过滤器及自然语言查询。

0 citationsRead paper

TailVis: Expressive Chart Refinement Preserving Data-Binding Integrity

Jul 28, 2026

This work addresses the limitations of existing data visualization tools, which often fail to support fine-grained visual customization while preserving data binding, thereby forcing users to resort to external graphic editors. To bridge this gap, we present TailVis, a system that extends the InfoVis reference model to encompass a post-rendering design phase. TailVis integrates element-level direct selection, natural language input, and dynamic GUI controls, augmented by referential interactions that enable data-aware, open-ended editing. The system maintains data-binding integrity through a dedicated preservation mechanism, employs an extensible selection model, and supports iterative design via provenance-aware history management. User studies demonstrate that TailVis significantly reduces repetitive operations and effectively enables expressive, data-consistent chart refinement within a unified environment.

0 citationsRead paper

"When to Hand Off, When to Work Together": Expanding Human-Agent Co-Creative Collaboration through Concurrent Interaction

Mar 02, 2026

This work addresses the challenge that current AI agents struggle to interpret users’ concurrent interaction intents on shared artifacts, thereby limiting dynamic co-creation. To overcome this, we propose CLEO—a collaborative intelligent agent grounded in mixed-initiative interaction principles—that dynamically switches among delegation, guidance, and collaboration modes by recognizing user concurrent behaviors in real time. We introduce the first collaborative model capable of real-time intent interpretation, identifying five behavioral patterns, six triggering mechanisms, and four enabling factors, and implement a decision framework comprising six interactive loops. Based on 214 rounds of interactions with professional designers, we quantitatively analyze mode usage (70.1% delegation, 28.5% guidance, 31.8% collaboration) and release design guidelines alongside a labeled dataset to support future research.

0 citationsRead paper

DiscoverLLM: From Executing Intents to Discovering Them

Feb 03, 2026

This work proposes DiscoverLLM, a framework designed to address the challenge of clarifying ambiguous or open-ended user requests whose underlying intents are often initially unspecified. By modeling users’ cognitive states through a hierarchical intent structure and leveraging a reinforcement learning–driven user simulator—where reward signals reflect the degree of intent concretization—the framework trains large language models to dynamically balance exploration and refinement during interaction, proactively guiding users toward intent discovery and clarification. Integrating hierarchical intent modeling with interactive alignment training, DiscoverLLM achieves performance improvements exceeding 10% across creative writing, technical writing, and SVG drawing tasks, while reducing dialogue length by up to 40%. A user study involving 75 participants demonstrates its significant superiority over baseline methods in both efficiency and user satisfaction.

0 citationsRead paper

Design Techniques for LLM-Powered Interactive Storytelling: A Case Study of the Dramamancer System

Jan 26, 2026

This work addresses the fundamental tension in interactive storytelling between authorial intent and player agency. It proposes Dramamancer, a novel design paradigm for large language model (LLM)-driven interactive narratives that reconciles these competing demands by parsing author-defined story schemata and integrating dynamic response mechanisms to player actions. Leveraging the generative capabilities of LLMs, the system produces narrative content in real time that adheres to underlying story logic while supporting high degrees of interactivity. Empirical evaluation demonstrates that this approach effectively balances narrative coherence with creative control and player autonomy. The study thus offers a reproducible design framework and evaluation pathway for LLM-powered interactive storytelling systems.

0 citationsRead paper