Relating a piece to previously established works is crucial in creating and engaging with art, but AI interfaces tend to obscure such relationships, rather than helping users explore them. Embedding models present new opportunities to support spatially exploring and relating artwork. We built Artographer, an art-exploration system featuring a zoomable 2-D map, constructed from similarity-clustered embeddings of ~16,000 historical artworks. We used Artographer as a design probe to explore how alternative artwork distribution interface design can shape media engagement: we invited 20 participants, including 9 art history scholars, to traverse the map, collecting artworks for a goal-driven task and while freely exploring. We identify values enacted in spatial art discovery (Visibility, Agency, Serendipity, Friction) and consider how these values challenge dominant design paradigms—in particular, the recommendation systems governing contemporary media distribution platforms. We reimagine a curatorial approach to media distribution, within digital ecosystems where history and culture can thrive.

Reflection and metacognition are central to the creative user experience. However, most HCI research on reflection focuses on clear, task-oriented goals such as to reflect on personal data or pedagogical outcomes. This contrasts with the open-ended and challenging to articulate goals of creative user experiences. For the first time, this workshop brings together interdisciplinary researchers, designers, educators, and artists across HCI, Cognitive Science, Design, AI, Learning Sciences, and Digital Art to examine reflection in creative interaction. The workshop will discuss themes, drawn from earlier discussions with HCI researchers and artists, on: how best to capture reflection in creative contexts, how to leverage the arts to support reflection for ethical change, and how to design creative AI that enhances – not hinders – critical thinking. By bringing interdisciplinary perspectives on reflection into discussion, the workshop will develop a guiding taxonomy for reflection in creative interaction to inform future creative practice and tool development.

Generative AI systems allow visual designers to rapidly produce many image alternatives, but preserving, revisiting, and building on promising partial results across iterations remains challenging. In practice, generated images are rarely valuable as complete wholes; instead, designers often reuse fragments, revisit earlier materials, and combine partial ideas into new directions. We present Trinketry, an element-centered visual exploration system built around trinkets: reusable visual and semantic elements extracted from prior generations. Trinketry allows users to extract image regions, whole images, text labels, and composite elements; recombine them in intention trays to generate new variations; trace the provenance of specific elements across the exploration process; and retrieve semantically related prior outcomes. By foregrounding extraction, recombination, tracing, and retrieval, this demo presents an alternative interaction model for AI-assisted visual exploration—one that supports traceable reuse, intentional iteration, and reflective design exploration.

Authors of LLM-based interactive digital narratives (IDNs) struggle to preserve creative intent as player choices and real-time generation pull storylines in unpredictable directions. Existing frameworks treat IDNs as static once published, limiting authors’ insight into and control over the storylines that emerge from unexpected player input in the wild. We propose cultivation: a design metaphor in which LLM-generated branches are stored as persistent material for authors to shape through iterative curation. Authors seed an initial scenario; the system grows new branches in response to player exploration; authors prune and revise what emerges, accumulating preference data that steers future generation. We demonstrate cultivation through Bonsai, an IDN authoring tool, and complement this design account with three simulated experiments showing that learned preferences transfer to unseen scenes, are project-specific rather than portable, and improve substantially when extraction is structured around IDN authoring categories. This metaphor reframes human-AI creative collaboration: authors become gardeners, tending ever-growing branches rather than constraining ephemeral outputs.

Creativity tools are a cornerstone of HCI, with systems for video, music, writing, and design deeply embedded in modern creative practice. Yet one key element of these systems remains undertheorized: the role of activity traces. Activity traces are the records of creator data, including artifact iterations, annotations, or reference materials, produced over the course of a creative process. To examine how activity traces are leveraged, we reviewed 133 creativity systems from major HCI venues. We structure our findings through a Living Framework for Trace Awareness, which captures both the characteristics of trace data and how systems engage with their temporal features. This framework offers the first systematic account of activity trace usage in creativity tools. We highlight overlooked assumptions about creator data in feature design and position activity traces as a core design material for shaping the next generation of creativity support systems.

According to the recently introduced theory of artistic support tools, creativity support tools exert normative influences over artistic production, instantiating a normative ground that shapes both the process and product of artistic expression.We argue that the normative ground of most existing automated writing tools is misaligned with writerly values and identify a potential alternative frame-material writing support-for experimental poetry tools that flexibly support the finding, processing, transforming, and shaping of text(s).Based on this frame, we introduce Phraselette, an artistic material writing support interface that helps experimental poets search for words and phrases.To provide material writing support, Phraselette is designed to counter the dominant mode of automated writing tools, while offering language model affordances in line with writerly values.We further report on an extended expert evaluation involving 10 published poets that indicates support for both our framing of material writing support and for Phraselette itself.

Figure 1: Fuzzy linkography allows for the rapid translation of user activity logs from digital creativity support tools (and other traces of creative activity) into rough graphical summaries, suitable for visual and quantitative inspection by researchers.

We introduce Toyteller, an AI-powered storytelling system where users generate a mix of story text and visuals by directly manipulating character symbols like they are toy-playing. Anthropomorphized symbol motions can convey rich and nuanced social interactions; Toyteller leverages these motions (1) to let users steer story text generation and (2) as a visual output format that accompanies story text. We enabled motion-steered text generation and text-steered motion generation by mapping motions and text onto a shared semantic space so that large language models and motion generation models can use it as a translational layer. Technical evaluations showed that Toyteller outperforms a competitive baseline, GPT-4o. Our user study identified that toy-playing helps express intentions difficult to verbalize. However, only motions could not express all user intentions, suggesting combining it with other modalities like language. We discuss the design space of toy-playing interactions and implications for technical HCI research on human-AI interaction.

Story generation has been a prominent application of Large Language Models (LLMs). However, understanding LLMs' ability to produce high-quality stories remains limited due to challenges in automatic evaluation methods and the high cost and subjectivity of manual evaluation. Computational narratology offers valuable insights into what constitutes a good story, which has been applied in the symbolic narrative planning approach to story generation. This work aims to deepen the understanding of LLMs' story generation capabilities by using them to solve narrative planning problems. We present a benchmark for evaluating LLMs on narrative planning based on literature examples, focusing on causal soundness, character intentionality, and dramatic conflict. Our experiments show that GPT-4 tier LLMs can generate causally sound stories at small scales, but planning with character intentionality and dramatic conflict remains challenging, requiring LLMs trained with reinforcement learning for complex reasoning. The results offer insights on the scale of stories that LLMs can generate while maintaining quality from different aspects. Our findings also highlight interesting problem solving behaviors and shed lights on challenges and considerations for applying LLM narrative planning in game environments.

Generative AI has established the opportunity to readily transform content from one medium to another.This capability is especially powerful for storytelling, where visual illustrations can illuminate a story originally expressed in text.In this paper, we focus on the task of narrative scene illustration, which involves automatically generating an image depicting a scene in a story.Motivated by recent progress on textto-image models, we consider a pipeline that uses LLMs as an interface for prompting textto-image models to generate scene illustrations given raw story text.We apply variations of this pipeline to a prominent story corpus in order to synthesize illustrations for scenes in these stories.We conduct a human annotation task to obtain pairwise quality judgments for these illustrations.The outcome of this process is the SCENEILLUSTRATIONS dataset, which we release as a new resource for future work on crossmodal narrative transformation.Through our analysis of this dataset and experiments modeling illustration quality, we demonstrate that LLMs can effectively verbalize scene knowledge implicitly evoked by story text.Moreover, this capability is impactful for generating and evaluating illustrations.

Large language models (LLMs) are now being used in a wide variety of contexts, including as creativity support tools (CSTs) intended to help their users come up with new ideas. But do LLMs actually support user creativity? We hypothesized that the use of an LLM as a CST might make the LLM’s users feel more creative, and even broaden the range of ideas suggested by each individual user, but also homogenize the ideas suggested by different users. We conducted a 36-participant comparative user study and found, in accordance with the homogenization hypothesis, that different users tended to produce less semantically distinct ideas with ChatGPT than with an alternative CST. Additionally, ChatGPT users generated a greater number of more detailed ideas, but felt less responsible for the ideas they generated. We discuss potential implications of these findings for users, designers, and developers of LLM-based CSTs.

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to examine and explore the multidimensional space of intelligent and interactive writing assistants. Through community collaboration, we explore five aspects of writing assistants: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions and codes by systematically reviewing 115 papers, while leveraging the expertise of researchers in various disciplines. Our design space aims to offer researchers and designers a practical tool to navigate, comprehend, and compare the various possibilities of writing assistants, and aid in the design of new writing assistants.

Large language models (LLMs) can help writers build story worlds by generating world elements, such as factions, characters, and locations. However, making sense of many generated elements can be overwhelming. Moreover, if the user wants to precisely control aspects of generated elements that are difficult to specify verbally, prompting alone may be insufficient. We introduce Patchview, a customizable LLM-powered system that visually aids worldbuilding by allowing users to interact with story concepts and elements through the physical metaphor of magnets and dust. Elements in Patchview are visually dragged closer to concepts with high relevance, facilitating sensemaking. The user can also steer the generation with verbally elusive concepts by indicating the desired position of the element between concepts. When the user disagrees with the LLM’s visualization and generation, they can correct those by repositioning the element. These corrections can be used to align the LLM’s future behaviors to the user’s perception. With a user study, we show that Patchview supports the sensemaking of world elements and steering of element generation, facilitating exploration during the worldbuilding process. Patchview provides insights on how customizable visual representation can help sensemake, steer, and align generative AI model behaviors with the user’s intentions.

In the 21st century workplace (especially in COVID times), much human social interaction occurs during virtual meetings. Unlike traditional screen-based remote meetings, VR meetings promise a more richly embodied form of communication. This paper maps the experiential terrain of seven commercial VR meeting applications, with a particular focus on the range of shared social experiences and collaborative abilities these applications may enable or constrain. We examine a range of applications including Spatial, Glue VR, MeetinVR, Mozilla Hubs, VRChat, AltspaceVR, and Rec Room. We analyze and map avatar system strategies, meeting environments and in-world cues, meeting invitation model, and different models of participation. In addition, we argue that commercial applications for meeting in VR that cater to workplace contexts might benefit from borrowing some of the strategies used in more leisure-focused environments for supporting social interaction.

Interactive emergent narrative games often make use of social simulation techniques, including the modeling of character relationships and knowledge, to generate compelling gameplay and stories. Existing attempts at simulating the spread of knowledge and opinions between characters, however, strictly limit the informational and social content of the communications that characters exchange, making it difficult to create play experiences in which gossip is a core mechanic. In this paper, we introduce gossip simulation as an open problem in intelligent narrative technologies and present an abstract approach to informationally and socially rich gossip simulation for emergent narrative-oriented social simulations, as well as a preliminary concrete implementation of this approach.

Theories of the poetics of procedural generation attempt to explain the player experience of interacting with generators by describing the aesthetic or experiential qualities that generators can afford when they are deployed in particular ways. We propose that an underinvestigated aspect of procgen poetics—the experiential effects of the sequencing of generated artifacts—can be understood in terms of hauntology, a theory of textual interpretation that aims to account for the lingering effects of past texts (and their implied futures) on present ones. We briefly introduce hauntology, discuss a few examples of hauntological effects in player experiences of procgen, and gesture at implications for future technical work.

Existing game description languages (GDLs) aspire to generality, but their focus on the specification of low-level mechanics leaves game generators that target these GDLs in the awkward position of having to invent combinations of mechanics that work well together from scratch. As a result, many existing game generators are good at producing games that contain novel and surprising combinations of mechanics, but bad at generating games that are readily interpretable by players as cultural artifacts. To address this problem, we introduce the concept of a genre-specific game description language (GSGDL): a game description language that deliberately encodes assumptions about a particular genre of games as a cultural form. As a proof of concept, we demonstrate the use of an internal representation of game structure used by the game creation tool GB Studio as a GSGDL for top-down 2D roleplaying games targeting the Game Boy. The use of this GSGDL gives us leverage to rapidly iterate on game generation features targeting a specific game genre and platform; to work with an existing toolchain that offers graphical editing, code generation, and automated play testing; and to more readily generate games that are interpretable by players as examples of a particular cultural form.

To date, the theatricality of videogames has been examined primarily through the lens of performance, a perspective that centers the liveness of theater and identifies the player with the role of the actor. However, another key facet of theatricality—the process of continuous reflective reinterpretation that characterizes theatrical production—has received less attention, despite its apparent applicability to the cyclical nature of many games. We conduct a reading of the narrative roguelike videogame Hades that emphasizes this reinterpretive process, and find that Hades is essentially structured around a sort of “diegetic backstage” that deliberately invites the player into the process of dramatic reinterpretation—leveraging the power of computation to prompt reflection on the game’s core themes and repeated remotivation of the game’s core gameplay. Our reading suggests that videogames, by shortening the reinterpretive loop that characterizes theatrical production and enabling players to experience many iterations of this loop within the comfort of their own home, can unlock a form of the pleasure that the members of a theater production derive from gradually bringing an initially flawed and disharmonious production into harmony.

Tabletop roleplaying games (TTRPGs) and procedural content generators can both be understood as systems of rules for producing content. In this paper, we argue that TTRPG design can usefully be viewed as procedural content generator design. We present several case studies linking key concepts from PCG research – including possibility spaces, expressive range analysis, and generative pipelines – to key concepts in TTRPG design. We then discuss the implications of these relationships and suggest directions for future work uniting research in TTRPGs and PCG.

We present Why Are We Like This? (WAWLT), a mixed-initiative, co-creative storytelling game in which two players develop a story transcript by selecting and editing actions to perform and narrativize in an ongoing simulation. In this paper, we lay out the major technical features of WAWLT’s AI architecture—including story sifting via Datalog queries, social simulation, action suggestions, and player-specified but system-understandable author goals—and discuss how these features work together to produce a play experience that facilitates player creativity.

Concepts utilizing applied ethics, such as responsible conduct of research (RCR), can prove difficult to teach due to the complexity of problems faced by researchers and the many underlying perspectives involved in such dilemmas. To address this issue, we created Academical, a choice-based interactive storytelling game for RCR education that enables players to experience a story from multiple perspectives. In this paper, we describe the design rationale of Academical, and present results from an initial study comparing it with traditional web-based educational materials from an existing university RCR course. The results highlight that utilizing a choice-based interactive story game is more effective for RCR education, with learners developing significantly higher engagement, stronger overall moral reasoning skills, and better knowledge scores for certain RCR topics.

Choice-driven narratives, such as those created through systems like Twine, are a compelling form of interactive storytelling that have been around for many years. But as long as this form has existed, it has grappled with a persistent design problem: consistently presenting choices that feel both effective and relevant. Brute force can achieve the desired effect, but usually at the cost of prohibitively high authorial burden. To tackle this, generative approaches, such as Mawhorter's Dunyazad, facilitate authoring procedural choice content for reuse and recombination. However, many such systems, while successful on technical levels, have yet to to be used to author large enough structures to support a full game, and require a high technical threshold for authors to use. To further development in this space, we present StoryAssembler, an open source generative narrative system that creates dynamic choice-driven narratives. It formed a critical part of Emma's Journey, an interactive narrative game, the initial version of which was collaboratively authored by a team of six writers. In the course of the game's creation, useful authoring patterns and design lessons were learned, as well as techniques that made the system approachable for first-time users.

This paper presents a case study in the experience-first prototyping of a generative game. Our goal in this process was to create a PCG-based mystery story construction game ncentered on a social simulation of characters and their motivations, and driven by a set of core themes and experiences we wanted players to encounter. In pursuit of this goal, we created a series of prototypes to test how a variety of generative and AI-based techniques---including character generation, character action suggestion based on game state, story sifting, and social simulation---may be used in support of collaborative storytelling. In this paper we catalogue these prototypes and what we have learned by creating them, detailing design elements we found to be successful in supporting player creativity and that may be useful to the developers of similar games and experiences going forward.

Most discussions of procedural content generation have focused primarily on the artifacts that generators produce or the process by which these artifacts are created. Less focus, however, has been placed on the methods by which generators interpret their input. Many generators take complex input, act as part of a generative pipeline, are part of a mixed-initiative communication with the user, or otherwise need to take context into account during generation. In these cases, the process by which the generator reads and makes sense of its input is often just as interesting as the process by which it produces an output artifact. It is worthwhile to take a closer look at how generators read. Via a case study of two erasure poetry generators, we propose the concept of a generativist reading: a process of reading that produces generative models. Many existing generators have dual input/output or reading/writing processes that are presented as a monolithic unit, but our understanding of both processes and results is enriched when we clearly distinguish between how generators write and how they read.

Gameplay involving player creativity can be both satisfying for players and enticing for designers to pursue, but understanding of how to design deliberately for player creativity remains limited. In this paper, we propose that a class of features previously identified as common elements of "gardening games"---including generativity, limited player control, and "incrementality" or "idleness"---are also particularly conducive to player creativity. By analyzing narrative artifacts created by players as retellings of their play experiences in games that implement these features, we highlight how these features enable players to overcome specific barriers to creativity. Based on this analysis, we then offer concrete suggestions to game designers who want to facilitate player creativity and propose ways that the design patterns discussed here might be extended to further support creative activity by players.

Immersive design fiction is a novel approach that embeds speculative interactions within a rich virtual reality (VR) storyworld. Immersive design fictions use VR to translate new design opportunities into story-driven, embodied experiences by positioning the participant as a character in a narrative world. This paper presents a case study of an immersive design fiction that depicts a fictionalized reimagining of an industry partner's work practices. This VR experience explores speculative interfaces for creative work and collaboration in the context of a fictional workplace environment. By placing design fictions within rich immersive contexts such as room-scale VR, researchers and practitioners can go beyond prototyping imagined interfaces to also speculate about the interaction rituals and surrounding social context within an experiential storyworld. This approach makes methodological and theoretical contributions to design fiction research by demonstrating a toolkit for exploring and reflecting upon the intersections between speculation, embodiment, and narrative context.