Mustafa Doga Dogan
Mustafa Doga Dogan has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Stefanie Mueller
MIT CSAIL, Cambridge, USA
6 shared publications - Eunyee Koh
Adobe Research, San Jose, California, USA
4 shared publications - Takeo Igarashi
The University of Tokyo, Tokyo, Japan
4 shared publications - Alexa Siu
Adobe Research, San Jose, California, USA
3 shared publications - Chang Xiao
Boston University, Boston, USA
3 shared publications - Raul Garcia-Martin
MIT CSAIL, United States and University Group for Identification Technologies, Universidad Carlos III de Madrid, Spain
3 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
UXCascade: Scalable Usability Testing with Simulated User Agents
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessUXCascade: Scalable Usability Testing with Simulated User Agents
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-13
InvisIto: Weaving Unobtrusive Infrared Markers for Ubiquitous Textile Interaction
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessInvisIto: Weaving Unobtrusive Infrared Markers for Ubiquitous Textile Interaction
- Open Access
- 19 June 2026
- Published by Elsevier in SSRN Electronic Journal
XAGEN: Designing Explainability Support for Failure Detection and Correction in Multi-Agent Workflows
The rapid adoption of LLM-powered multi-agent systems has brought users with diverse AI expertise—from software developers to domain experts—into the process of building and maintaining complex agentic workflows. Yet when these distributed systems fail, their non-deterministic and opaque nature makes it difficult for users to observe, attribute, and correct errors. To understand practitioners’ needs, we conducted formative interviews with 12 practitioners spanning AI developers who build agentic systems to domain experts who utilize them, surfacing five key challenge themes and four design goals for explainability tools. Building on these insights, we designed XAGEN, an explainability interface that supports failure detection and correction through three capabilities: log visualization for glanceable workflow understanding, human-in-the-loop feedback to capture expert judgment, and automatic error identification via an LLM-as-a-judge. In a user evaluation with 8 participants, XAGEN was rated significantly higher than a state-of-the-art observability baseline across all four dimensions—understanding, usability, helpfulness, and satisfaction—with median scores of 6–7 out of 7 (all p < 0.05). All three features were rated useful: log visualization received the highest helpfulness rating (median = 5/5, p < 0.01), followed by automatic error identification (median = 4.5/5, p < 0.05) and human-in-the-loop output feedback (median = 4/5, p = 0.07). Our findings yield empirically grounded design guidelines for explainable agentic AI and highlight open challenges for context-aware interactive debugging of multi-agent workflows.
- 19 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessXAGEN: Designing Explainability Support for Failure Detection and Correction in Multi-Agent Workflows
The rapid adoption of LLM-powered multi-agent systems has brought users with diverse AI expertise—from software developers to domain experts—into the process of building and maintaining complex agentic workflows. Yet when these distributed systems fail, their non-deterministic and opaque nature makes it difficult for users to observe, attribute, and correct errors. To understand practitioners’ needs, we conducted formative interviews with 12 practitioners spanning AI developers who build agentic systems to domain experts who utilize them, surfacing five key challenge themes and four design goals for explainability tools. Building on these insights, we designed XAGEN, an explainability interface that supports failure detection and correction through three capabilities: log visualization for glanceable workflow understanding, human-in-the-loop feedback to capture expert judgment, and automatic error identification via an LLM-as-a-judge. In a user evaluation with 8 participants, XAGEN was rated significantly higher than a state-of-the-art observability baseline across all four dimensions—understanding, usability, helpfulness, and satisfaction—with median scores of 6–7 out of 7 (all p < 0.05). All three features were rated useful: log visualization received the highest helpfulness rating (median = 5/5, p < 0.01), followed by automatic error identification (median = 4.5/5, p < 0.05) and human-in-the-loop output feedback (median = 4/5, p = 0.07). Our findings yield empirically grounded design guidelines for explainable agentic AI and highlight open challenges for context-aware interactive debugging of multi-agent workflows.
- Open Access
- 12 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 613-617
Demonstration of MiXR: Harvesting and Recomposing Geometry from Real-World Objects for In-Situ 3D Design
Recent developments in 3D generative AI enable users to create bespoke 3D models from text or image prompts. However, language is often insufficient to express spatial design intent, and customization of generative output remains limited to surface appearance, making it difficult to personalize designs to the geometry and constraints of a user’s environment. Bridging this gap typically requires returning to conventional CAD tools to measure, edit, and adapt geometry, tasks that remain time-consuming and error-prone. We present MiXR, an augmented reality system that enables users to create new 3D designs by remixing parts harvested from real-world objects. Users paint to segment real-world geometry into reusable parts, recompose the parts directly in AR through spatial manipulation, and refine the assembly into a unified, fabrication-ready 3D model via a generative AI pipeline. By treating spatial assembly itself as the input modality, MiXR replaces text prompting with rough physical arrangement as a more reliable and expressive way to specify design intent. In this demonstration, attendees will construct novel 3D models by harvesting parts from objects in their environment, recomposing them in AR, and refining them with generative AI into coherent unified designs.
- 12 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 613-617
Open AccessDemonstration of MiXR: Harvesting and Recomposing Geometry from Real-World Objects for In-Situ 3D Design
Recent developments in 3D generative AI enable users to create bespoke 3D models from text or image prompts. However, language is often insufficient to express spatial design intent, and customization of generative output remains limited to surface appearance, making it difficult to personalize designs to the geometry and constraints of a user’s environment. Bridging this gap typically requires returning to conventional CAD tools to measure, edit, and adapt geometry, tasks that remain time-consuming and error-prone. We present MiXR, an augmented reality system that enables users to create new 3D designs by remixing parts harvested from real-world objects. Users paint to segment real-world geometry into reusable parts, recompose the parts directly in AR through spatial manipulation, and refine the assembly into a unified, fabrication-ready 3D model via a generative AI pipeline. By treating spatial assembly itself as the input modality, MiXR replaces text prompting with rough physical arrangement as a more reliable and expressive way to specify design intent. In this demonstration, attendees will construct novel 3D models by harvesting parts from objects in their environment, recomposing them in AR, and refining them with generative AI into coherent unified designs.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Weaving and Disguising Infrared Markers toward Invisible Textile Interaction
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessWeaving and Disguising Infrared Markers toward Invisible Textile Interaction
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
XAgen: An Explainability Tool for Identifying and Correcting Failures in Multi-Agent Workflows
As multi-agent systems powered by Large Language Models (LLMs) are increasingly adopted in real-world workflows, users with diverse technical backgrounds are now building and refining their own agentic processes. However, these systems can fail in opaque ways, making it difficult for users to observe, understand, and correct errors. We conducted formative interviews with 12 practitioners to identify mismatches between existing debugging tools and users’ needs. Based on these insights, we designed XAgen, an explainability tool that supports users with varying AI expertise through three core capabilities: log visualization for glanceable workflow understanding, human-in-the-loop feedback to capture expert judgment, and automatic error detection via an LLM-as-a-judge. In a user study with 8 participants, XAgen helped users locate failures more easily, attribute to specific agents or steps, and iteratively improve configurations. Our findings surface human-centered design guidelines for explainable agentic AI development and highlight opportunities for more context-aware interactive debugging.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessXAgen: An Explainability Tool for Identifying and Correcting Failures in Multi-Agent Workflows
As multi-agent systems powered by Large Language Models (LLMs) are increasingly adopted in real-world workflows, users with diverse technical backgrounds are now building and refining their own agentic processes. However, these systems can fail in opaque ways, making it difficult for users to observe, understand, and correct errors. We conducted formative interviews with 12 practitioners to identify mismatches between existing debugging tools and users’ needs. Based on these insights, we designed XAgen, an explainability tool that supports users with varying AI expertise through three core capabilities: log visualization for glanceable workflow understanding, human-in-the-loop feedback to capture expert judgment, and automatic error detection via an LLM-as-a-judge. In a user study with 8 participants, XAgen helped users locate failures more easily, attribute to specific agents or steps, and iteratively improve configurations. Our findings surface human-centered design guidelines for explainable agentic AI development and highlight opportunities for more context-aware interactive debugging.
- Top Cited PapersOpen Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 376-392
UI Remix: Supporting UI Design Through Interactive Example Retrieval and Remixing
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 376-392
Top Cited PapersOpen AccessUI Remix: Supporting UI Design Through Interactive Example Retrieval and Remixing
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-19
TinkerXR: In-Situ, Reality-Aware CAD and 3D Printing Interface for Novices
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessTinkerXR: In-Situ, Reality-Aware CAD and 3D Printing Interface for Novices
- Open Access
- 5 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 526-532
ImprovMate: Multimodal AI Assistant for Improv Actor Training
- 5 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 526-532
Open AccessImprovMate: Multimodal AI Assistant for Improv Actor Training
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-16
XR-penter: Material-Aware and In Situ Design of Scrap Wood Assemblies
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Open AccessXR-penter: Material-Aware and In Situ Design of Scrap Wood Assemblies