{"total":17,"items":[{"citing_arxiv_id":"2605.15848","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Conversations in Space: Structuring Non-Linear LLM Interactions on a Canvas","primary_cat":"cs.HC","submitted_at":"2026-05-15T11:01:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CanvasConvo presents a spatial canvas interface for branching LLM conversations, evaluated in a 5-7 day field study with 24 participants that found support for exploratory workflows.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11344","ref_index":80,"ref_count":4,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Making Abstraction Concrete: A Design Space and Interaction Model of Abstraction in Interactive Systems","primary_cat":"cs.HC","submitted_at":"2026-05-11T23:54:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A survey of 457 papers yields a six-dimensional design space for abstraction in interactive systems that reframes gulfs of execution and evaluation while articulating cognitive and design processes for bridging abstraction gaps.","context_count":2,"top_context_role":"background","top_context_polarity":"support","context_text":"Research in linguistics, visual and spatial cognition has found that people fluidly shift the levels of abstraction to commu- nicate a concept via natural language expressions [57] as well as visual or gestural depictions [157]. In the field of semiotics and visu- alization, encoding information and data using visual symbols has been seen as a process of forming a visual abstraction of informa- tion [161]. Utilizing the gradual transition of a concrete depiction of a problem to a more abstract one to facilitate knowledge under- standing, also known as concreteness fading, has been established as an effective pedagogical methodology [22, 47]. Research in artifi- cial intelligence explores invoking the abstraction process in LLMs to increase their performance on various reasoning tasks [189]."},{"citing_arxiv_id":"2604.21205","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"When Constraints Limit and Inspire: Characterizing Presentation Authoring Practices for Evolving Narratives","primary_cat":"cs.HC","submitted_at":"2026-04-23T01:53:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Presenters treat constraints as active guides for building and reusing slide narratives across sessions, supported by the new CMPA framework and ReSlide tool that improves constraint-aware authoring compared to baselines.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"prone [61], motivating a range of tools supporting reuse across authoring sessions. One line of work conceptualizes reuse primarily as a data-management problem. Commercial platforms such as SlideLizard1, SlideCamp2, Shufflrr3, and Empower4 utilized a centralized library where presen- tation decks can be stored and shared between a central deck and local copies within organizations and collaborations [35]. Moving 1https://slidelizard.com/en 2https://slidecamp.io/ 3https://shufflrr.com/ 4https://www.empowersuite.com/en/ Woodstock '18, June 03-05, 2018, Woodstock, NY Trovato and Tobin, et al. forward, more researches focus on content reuse in diverse scenar- ios [10], slide content retrieval algorithms [ 48, 61, 72], semantic- based slide re-adaptation [64], slide structural relationship extrac-"},{"citing_arxiv_id":"2604.19423","ref_index":83,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Allow Me Into Your Dream: A Handshake-and-Pull Protocol for Sharing Mixed Realities in Spontaneous Encounters","primary_cat":"cs.HC","submitted_at":"2026-04-21T12:53:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TouchPort collapses the multi-stage process of discovering, consenting to, and syncing mixed reality encounters into one embodied handshake-and-pull gesture.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"1145/2580723.2580730 [82] Bektur Ryskeldiev, Yoichi Ochiai, Michael Cohen, and Jens Herder. 2018. Dis- tributed Metaverse: Creating Decentralized Blockchain-based Model for Peer- to-peer Sharing of Virtual Spaces for Mixed Reality Applications. InProceed- ings of the 9th Augmented Human International Conference (AH2018). ACM, 1-3. doi:10.1145/3174910.3174952 [83] Alexander Schäfer, Gerd Reis, and Didier Stricker. 2022. A Survey on Synchronous Augmented, Virtual, and Mixed Reality Remote Collaboration Systems.Comput. Surveys55, 6 (2022). doi:10.1145/3533376 [84] Jan-Henrik Schröder, Daniel Schacht, Niklas Peper, Anita Marie Hamurculu, and Hans-Christian Jetter. 2023. Collaborating Across Realities: Analytical Lenses for"},{"citing_arxiv_id":"2604.19114","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OOPrompt: Reifying Intents into Structured Artifacts for Modular and Iterative Prompting","primary_cat":"cs.HC","submitted_at":"2026-04-21T05:48:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"OOPrompt reifies user intents into structured manipulable artifacts to enable modular and iterative prompting in LLM-based interactive systems.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"which first associates prompts with OOP to leverage the fact that programming languages are designed for efficient communication with machines. Specifically, it proposes a \"dual-layer prompt design framework\" that conceptualizes prompts as software projects, with modules and elements analogous to classes and methods to hier- archically address high-level intents and specific instructions [44]. However,LangGPTmainly focuses on the conceptual framework and validating it on existing LLMs; meanwhile, it remains unclear how user interfaces can appropriately support users to apply this idea to compose prompts as objects. Our work builds on the same OOP foundation and fills in this gap by formalizing theOOPrompt interaction paradigm. 3.2 Interactive Interface Design Examples"},{"citing_arxiv_id":"2604.12949","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GlintMarkers: Spatial Perception on XR Eyewear using Corneal Reflections","primary_cat":"cs.HC","submitted_at":"2026-04-14T16:45:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"GlintMarkers performs gaze-driven spatial perception on XR eyewear by extracting distance, orientation, and identity from corneal reflections of retroreflective markers using inward cameras.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12624","ref_index":55,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GraphTide: Augmenting Knowledge-Intensive Text with Progressive Nested Graph","primary_cat":"cs.HC","submitted_at":"2026-04-14T11:52:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GraphTide augments text with animated progressive nested entity-relationship graphs to improve comprehension over traditional or static graph methods.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"approaches have attempted to address this by explicitly structuring entities and their relationships, for example through graph-based visualizations or hierarchical canvas designs. However, single-layer graphs, such as those used in Graphologue [28], fall short in representing the nested structure of complex sentences, leading to representations that are either too coarse or too fragmented. Similarly, hierarchical canvas-based designs, such as Sensecape [55], organize information across multiple levels of abstraction but require users to switch between canvases, introducing interaction overhead and increasing cognitive load. For knowledge-intensive text comprehension, we aim for a simplified visualization that explicitly reveals intra-sentence structural relationships and is intended to better align with readers' mental models, thereby supporting them in analyzing sentence structure and extracting key information"},{"citing_arxiv_id":"2604.11538","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ResearchCube: Multi-Dimensional Trade-off Exploration for Research Ideation","primary_cat":"cs.HC","submitted_at":"2026-04-13T14:32:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ResearchCube provides a 3D spatial interface with bipolar trade-off dimensions and direct-manipulation interactions to support multi-dimensional research ideation, shown helpful in a study with 11 researchers for externalizing thinking and increasing agency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10587","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CogInstrument: Modeling Cognitive Processes for Bidirectional Human-LLM Alignment in Planning Tasks","primary_cat":"cs.HC","submitted_at":"2026-04-12T11:15:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CogInstrument represents human reasoning as revisable cognitive motifs in graphical form to support iterative alignment with LLMs during planning tasks, with a N=12 study indicating gains in targeted revision, agency, and trust over standard dialogue interfaces.","context_count":1,"top_context_role":"background","top_context_polarity":"support","context_text":"ize decision structures or task graphs from user behavior, while CausalMapper uses causal maps and LLM prompting to support mixed-initiative reflection [25, 50, 72]. These systems show that externalization can improve reflection and coordination, but they do not provide a shared representation for inspecting and revising user-grounded reasoning across tasks [57]. 2.2 Human-LLM Alignment Recent work on human-LLM alignment addresses the gap between internal mental states and model outputs [36, 48, 75]. Most existing systems, however, externalize either user-side goals or model-side interpretations, while leaving underspecified the reasoning struc- ture that connects them. CogInstrument Conference acronym 'XX, June 03-05, 2018, Woodstock, NY"},{"citing_arxiv_id":"2604.10575","ref_index":62,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"NexusAI: Enabling Design Space Exploration of Ideas through Cognitive Abstraction and Functional Decomposition","primary_cat":"cs.HC","submitted_at":"2026-04-12T10:41:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"NexusAI decomposes LLM inspirations into navigable functional fragments and abstractions to improve creative design space exploration, with a user study showing reduced cognitive overhead.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[61] Leong-Hwee Teo, Bonnie John, and Marilyn Blackmon. 2012. CogTool-Explorer: a model of goal-directed user exploration that considers information layout. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (Austin, Texas, USA)(CHI '12). Association for Computing Machinery, New York, NY, USA, 2479-2488. doi:10.1145/2207676.2208414 [62] Anqi Wang, Zhengyi Li, Xin Tong, and Pan Hui. 2026. DesignerlyLoop: Form- ing Design Intent through Curated Reasoning for Human-LLM Alignment. arXiv:2511.15331 [cs.HC] https://arxiv.org/abs/2511.15331 [63] Penglei Wang, Ziming Quan, Danyang Wu, and Jin Xu. 2025. Cluster-Aware Contrastive Multi-View Clustering Based on Masked Views. InProceedings of"},{"citing_arxiv_id":"2604.09438","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Intent Lenses: Inferring Capture-Time Intent to Transform Opportunistic Photo Captures into Structured Visual Notes","primary_cat":"cs.HC","submitted_at":"2026-04-10T15:53:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Intent Lenses infer capture-time user intent from photos via LLMs to create dynamic, reusable interactive objects that generate and organize structured visual notes for later sensemaking.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"what is relevant, and reorganize it into meaningful representations [35]. Early efforts aimed to assist note-taking by scaffolding cap- ture [5, 13, 21, 38, 40], linking [6, 14, 34, 38, 44], and organization [3, 31, 47, 48, 50], while leaving composition of notes largely to the user. For example, NoteLook [6] integrates video with ink annota- tions to support revisitation, and LiquidText [48] enables flexible excerpt manipulation and spatial reorganization to facilitate syn- thesis. More recent systems have considered how notes can be automatically generated [7, 16, 25, 43, 54, 58] or expanded upon using AI. For instance, NoTeeLine [15] expands short user-authored micronotes into fuller notes while preserving writing style using LLMs. Across these approaches, note-taking continues to rely on"},{"citing_arxiv_id":"2604.08898","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Omakase: proactive assistance with actionable suggestions for evolving scientific research projects","primary_cat":"cs.HC","submitted_at":"2026-04-10T03:05:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Omakase monitors project documents to infer timely queries and distills research reports into actionable suggestions that users rated significantly more useful than raw reports.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[22] Hyeonsu B Kang, Rafal Kocielnik, Andrew Head, Jiangjiang Yang, Matt Latzke, Aniket Kittur, Daniel S Weld, Doug Downey, and Jonathan Bragg. 2022. From Who You Know to What You Read: Augmenting Scientific Recommendations with Implicit Social Networks. InProceedings of the 2022 CHI Conference on Human Factors in Computing Systems. doi:10.1145/3491102.3517470 [23] Hyeonsu B Kang, Sherry Wu, Joseph Chee Chang, and A. Kittur. 2023. Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemaking.Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (2023). doi:10.1145/3586183.3606759 [24] Rodney Michael Kinney, Chloe Anastasiades, Russell Authur, Iz Beltagy, Jonathan"},{"citing_arxiv_id":"2604.07121","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mixed-Initiative Context: Structuring and Managing Context for Human-AI Collaboration","primary_cat":"cs.HC","submitted_at":"2026-04-08T14:16:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Mixed-Initiative Context reconceptualizes interaction context as a dynamic, jointly manageable structure that humans and AI can actively organize according to task needs.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[47] Sangho Suh, Bryan Min, Srishti Palani, and Haijun Xia. 2023. Sensecape: En- abling Multilevel Exploration and Sensemaking with Large Language Models. InProceedings of the 36th Annual ACM Symposium on User Interface Software and Technology(San Francisco, CA, USA)(UIST '23). Association for Computing Machinery, New York, NY, USA, Article 1, 18 pages. doi:10.1145/3586183.3606756 [48] Michelle Vaccaro, Abdullah Almaatouq, and Thomas Malone. 2024. When com- binations of humans and AI are useful: A systematic review and meta-analysis. Nature Human Behaviour8, 12 (2024), 2293-2303. [49] Qian Wan, Siying Hu, Yu Zhang, Piaohong Wang, Bo Wen, and Zhicong Lu. 2024. \"It Felt Like Having a Second Mind\": Investigating Human-AI Co-creativity in"},{"citing_arxiv_id":"2512.02288","ref_index":56,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Artographer: a Curatorial Interface for Art Space Exploration","primary_cat":"cs.HC","submitted_at":"2025-12-02T00:03:10+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Artographer is a zoomable 2D embedding-based map for art exploration, evaluated in a study with 20 participants to surface values of Visibility, Agency, Serendipity, and Friction that challenge recommendation-driven media distribution.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.13742","ref_index":85,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Spatial Balancing: Harnessing Spatial Reasoning to Balance Scientific Exposition and Narrative Engagement in LLM-assisted Science Communication Writing","primary_cat":"cs.HC","submitted_at":"2025-09-17T06:50:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SpatialBalancing is a system that turns revision trade-offs into spatial navigation so writers can iteratively balance scientific exposition and narrative engagement with LLM assistance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.22163","ref_index":62,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"IdeaBlocks: Expressing and Reusing Divergent Intents for Graphic Design Exploration using Generative AI","primary_cat":"cs.HC","submitted_at":"2025-07-29T18:53:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"IdeaBlocks modularizes divergent intents into Exploration Blocks with multi-level reuse options, enabling 2.13 times more images explored and 12.5% greater visual diversity than baseline in a comparative user study.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.21582","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents","primary_cat":"cs.CL","submitted_at":"2025-06-17T05:24:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"VIDEE introduces a human-in-the-loop system using Monte-Carlo Tree Search for task decomposition, executable pipeline generation, and LLM-based evaluation with visualizations to support non-expert text analytics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}