AI-Driven Usability Testing: Integrating Eye-Tracking Data and Agentic Systems for Automated UI Evaluation
Open accessAbstract
Despite the benefits of user interface/experience (UI/UX) design, traditional usability testing remains resource-intensive and repetitive. This study proposes a novel system that integrates real-time browser-based eye-tracking with a multimodal agentic framework to automate UI evaluation. Participants interacted with task-specific interfaces while their gaze data was captured and analysed by a multi-agent system to generate structured usability reports grounded in heuristic principles. Precision metrics were used to quantify qualitative insights, enabling measurable evaluation. To enhance accessibility, a comparative analysis was conducted between proprietary and open-source Large Language Models (LLMs). Results showed that proprietary models consistently delivered accurate insights, whereas smaller local models struggled with reliability — highlighting future directions for offline deployment. The findings contribute to the advancement of AI-driven solutions in usability evaluation, showcasing how agentic systems integrated with browser-based eye-tracking tools can overcome traditional limitations.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Collapsing perception, interpretation, and evaluation into a single step constrains an AI system's ability to reason in a grounded, context-sensitive manner, often yielding generic, weakly anchored feedback that is difficult to adapt to task or context.
“For the AI, collapsing perception, interpretation, and evaluation into a single step constrains its ability to reason in a grounded, context-sensitive manner, often yielding feedback that is generic, weakly anchored in the concrete screen, and difficult to adapt to task or context [17, 48].”
From Criticmate: Stagewise Human–AI Co-Critique in Single-Screen UI Evaluation (2026) · cites this paper as [48]
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measuredPrior work reports frequent misrecognition of UI structure, limited sensitivity to design intent, and weakly actionable critiques in current AI UI evaluation systems.
“Prior work reports frequent misrecognition of UI structure [34, 94], limited sensitivity to design intent [17, 57], and weakly actionable critiques [48].”
From Criticmate: Stagewise Human–AI Co-Critique in Single-Screen UI Evaluation (2026) · cites this paper as [48]
These limitations echo prior observations that LLM-based critique cannot fully replace human judgment.
“These limitations echo prior observations that LLMbased critique cannot fully replace human judgment [17, 48].”
From Criticmate: Stagewise Human–AI Co-Critique in Single-Screen UI Evaluation (2026) · cites this paper as [48]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 35
- Bang, Y.; Cahyawijaya, S.; Lee, N.; Dai, W.; Su, D.; Wilie, B.; Lovenia, H.; Ji, Z.; Yu, T.; Chung, W.; Do, Q. V.; Xu, Y.; and Fung, P. 2023. A Multitask, Multilingual, Multi- modal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity. ArXiv, abs/2302.04023. · arXiv
- Bertão, R. A.; and Joo, J. 2021. Artificial intelligence in UX/UI design: a survey on current adoption and [future] practices. Blucher Design Proceedings.
- Chen, W.; Su, Y.; Zuo, J.; Yang, C.; Yuan, C.; Qian, C.; Chan, C.-M.; Qin, Y.; Lu, Y.-T.; Xie, R.; Liu, Z.; Sun, M.; and Zhou, J. 2023. AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents. ArXiv, abs/2308.10848. · arXiv
- Chin, J. P.; Diehl, V. A.; and Norman, K. L. 1988. Devel- opment of an instrument measuring user satisfaction of the human-computer interface. In International Conference on Human Factors in Computing Systems.
- Dohan, D.; Xu, W.; Lewkowycz, A.; Austin, J.; Bieber, D.; Lopes, R. G.; Wu, Y.; Michalewski, H.; Saurous, R. A.; Sohl-Dickstein, J. N.; Murphy, K.; and Sutton, C. 2022. Lan- guage Model Cascades. ArXiv, abs/2207.10342. · arXiv
- Duan, P.; Warner, J.; Li, Y.; and Hartmann, B. 2024. Gener- ating Automatic Feedback on UI Mockups with Large Lan- guage Models. Proceedings of the CHI Conference on Hu- man Factors in Computing Systems.
- Gajos, K. Z.; and Weld, D. S. 2005. Preference elicitation for interface optimization. Proceedings of the 18th annual ACM symposium on User interface software and technology.
- Ge, Y.; Zhao, S.; Zeng, Z.; Ge, Y.; Li, C.; Wang, X.; and Shan, Y. 2023. Making LLaMA SEE and Draw with SEED Tokenizer. ArXiv, abs/2310.01218. · arXiv
- Haddad, S.; Latifzadeh, K.; Duraisamy, S.; Vanderdonckt, J.; Dâassi, O.; Belghith, S.; and Leiva, L. A. 2024. Good GUIs, Bad GUIs: Affective Evaluation of Graphical User Interfaces. Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization.
- Hong, S.; Zheng, X.; Chen, J. P.; Cheng, Y.; Zhang, C.; Wang, Z.; Yau, S. K. S.; Lin, Z. H.; Zhou, L.; Ran, C.; Xiao, L.; and Wu, C. 2023. MetaGPT: Meta Program- ming for Multi-Agent Collaborative Framework. ArXiv, abs/2308.00352. · arXiv
- Huang, R.; Huang, J.-B.; Yang, D.; Ren, Y.; Liu, L.; Li, M.; Ye, Z.; Liu, J.; Yin, X.; and Zhao, Z. 2023. Make-An- Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models. In International Conference on Machine Learning.
- Li, G.; Hammoud, H.; Itani, H.; Khizbullin, D.; and Ghanem, B. 2023. CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Soci- ety. ArXiv, abs/2303.17760. · arXiv
- Miniukovich, A.; and Angeli, A. D. 2015. Computation of Interface Aesthetics. Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems.
- Nielsen, J. 1994. Enhancing the explanatory power of us- ability heuristics. Conference Companion on Human Fac- tors in Computing Systems.
- Novák, J. .; Masner, J.; Benda, P.; Simek, P.; and Merunka, V. 2023. Eye Tracking, Usability, and User Experience: A Systematic Review. Int. J. Hum. Comput. Interact., 40: 4484-4500.
- Noh, H.; Ouyang, L.; O'Keefe, C.; Pachocki, J.; Paino, A.; Palermo, J.; Pantuliano, A.; Paras- candolo, G.; Parish, J.; Parparita, E.; Passos, A.; Pavlov, M.; Peng, A.; Perelman, A.; de Avila Belbute Peres, F.; Petrov, M.; de Oliveira Pinto, H. P.; Michael; Pokorny; Pokrass, M.; Pong, V. H.; Powell, T.; Power, A.; Power, B.; Proehl, E.; Puri, R.; Radford, A.; Rae, J.; Ramesh, A.; Raymond, C.; Real, F.; Rimbach, K.; Ross, C.; Rotsted, B.; Roussez, H.; Ryder, N.; Saltarelli, M.; Sanders, T.; Santurkar, S.; Sastry, G.; Schmidt, H.; Schnurr, D.; Schulman, J.; Sel- sam, D.; Sheppard, K.; Sherbakov, T.; Shieh, J.; Shoker, S.; Shyam, P.; Sidor, S.; Sigler, E.; Simens, M.; Sitkin, J.; Slama, K.; Sohl, I.; Sokolowsky, B.; Song, Y.; Staudacher, N.; Such, F. P.; Summers, N.; Sutskever, I.; Tang, J.; Tezak, N.; Thompson, M. B.; Tillet, P.; Tootoonchian, A.; Tseng, E.; Tuggle, P.; Turley, N.; Tworek, J.; Uribe, J. F. C.; Val- lone, A.; Vijayvergiya, A.; Voss, C.; Wainwright, C.; Wang, J. J.; Wang, A.; Wang, B.; Ward, J.; Wei, J.; Weinmann, C.; Welihinda, A.; Welinder, P.; Weng, J.; Weng, L.; Wiethoff, M.; Willner, D.; Winter, C.; Wolrich, S.; Wong, H.; Work- man, L.; Wu, S.; Wu, J.; Wu, M.; Xiao, K.; Xu, T.; Yoo, S.; Yu, K.; Yuan, Q.; Zaremba, W.; Zellers, R.; Zhang, C.; Zhang, M.; Zhao, S.; Zheng, T.; Zhuang, J.; Zhuk, W.; and Zoph, B. 2024. GPT-4 Technical Report. arXiv:2303.08774. · arXiv
- Pandian, V. P. S.; Suleri, S.; Beecks, C.; and Jarke, M. 2020. MetaMorph: AI Assistance to Transform Lo-Fi Sketches to Higher Fidelities. Proceedings of the 32nd Australian Con- ference on Human-Computer Interaction.
- Papoutsaki, A.; Sangkloy, P.; Laskey, J.; Daskalova, N.; Huang, J.; and Hays, J. 2016. WebGazer: Scalable Web- cam Eye Tracking Using User Interactions. In International Joint Conference on Artificial Intelligence.
- Park, J. S.; O'Brien, J. C.; Cai, C. J.; Morris, M. R.; Liang, P.; and Bernstein, M. S. 2023. Generative Agents: Inter- active Simulacra of Human Behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology.
- Rombach, R.; Blattmann, A.; Lorenz, D.; Esser, P.; and Om- mer, B. 2021. High-Resolution Image Synthesis with La- tent Diffusion Models. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10674- 10685.
- Shen, L.; Li, H.; Wang, Y.; and Qu, H. 2024. From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent Systems. ArXiv, abs/2408.03876. · arXiv
- Zamani, E. D.; Mikalef, P.; and Zhu, Y. 2023. Ar- tificial intelligence (AI) for user experience (UX) design: a systematic literature review and future research agenda. Inf. Technol. People, 37: 2324-2352.
- Sun, Q.; Yu, Q.; Cui, Y.; Zhang, F.; Zhang, X.; Wang, Y.; Gao, H.; Liu, J.; Huang, T.; and Wang, X. 2023. Generative Pretraining in Multimodality. ArXiv, abs/2307.05222. · arXiv
- Talebirad, Y.; and Nadiri, A. 2023. Multi-Agent Collab- oration: Harnessing the Power of Intelligent LLM Agents. ArXiv, abs/2306.03314. · arXiv
- Tang, Z.; Yang, Z.; Khademi, M.; Liu, Y.; Zhu, C.; and Bansal, M. 2023a. CoDi-2: In-Context, Interleaved, and In- teractive Any-to-Any Generation. 2024 IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR), 27415-27424.
- Tang, Z.; Yang, Z.; Zhu, C.; Zeng, M.; and Bansal, M. 2023b. Any-to-Any Generation via Composable Diffusion. ArXiv, abs/2305.11846. · arXiv
- Team, G.; Kamath, A.; Ferret, J.; Pathak, S.; Vieillard, N.; Merhej, R.; Perrin, S.; Matejovicova, T.; Ramé, A.; Rivière, M.; Rouillard, L.; Mesnard, T.; Cideron, G.; bastien Grill, J.; Ramos, S.; Yvinec, E.; Casbon, M.; Pot, E.; Penchev, I.; Liu, G.; Visin, F.; Kenealy, K.; Beyer, L.; Zhai, X.; Tsit- sulin, A.; Busa-Fekete, R.; Feng, A.; Sachdeva, N.; Cole- man, B.; Gao, Y.; Mustafa, B.; Barr, I.; Parisotto, E.; Tian, D.; Eyal, M.; Cherry, C.; Peter, J.-T.; Sinopalnikov, D.; Bhu- patiraju, S.; Agarwal, R.; Kazemi, M.; Malkin, D.; Kumar, R.; Vilar, D.; Brusilovsky, I.; Luo, J.; Steiner, A.; Friesen, A.; Sharma, A.; Sharma, A.; Gilady, A. M.; Goedeckemeyer, A.; Saade, A.; Feng, A.; Kolesnikov, A.; Bendebury, A.; Abdagic, A.; Vadi, A.; György, A.; Pinto, A. S.; Das, A.; Bapna, A.; Miech, A.; Yang, A.; Paterson, A.; Shenoy, A.; Chakrabarti, A.; Piot, B.; Wu, B.; Shahriari, B.; Petrini, B.; Chen, C.; Lan, C. L.; Choquette-Choo, C. A.; Carey, C.; Brick, C.; Deutsch, D.; Eisenbud, D.; Cattle, D.; Cheng, D.; Paparas, D.; Sreepathihalli, D. S.; Reid, D.; Tran, D.; Zelle, D.; Noland, E.; Huizenga, E.; Kharitonov, E.; Liu, F.; Amirkhanyan, G.; Cameron, G.; Hashemi, H.; Klimczak- Plucińska, H.; Singh, H.; Mehta, H.; Lehri, H. T.; Hazimeh, H.; Ballantyne, I.; Szpektor, I.; Nardini, I.; Pouget-Abadie, J.; Chan, J.; Stanton, J.; Wieting, J.; Lai, J.; Orbay, J.; Fer- nandez, J.; Newlan, J.; yeong Ji, J.; Singh, J.; Black, K.; Yu, K.; Hui, K.; Vodrahalli, K.; Greff, K.; Qiu, L.; Valen- tine, M.; Coelho, M.; Ritter, M.; Hoffman, M.; Watson, M.; Chaturvedi, M.; Moynihan, M.; Ma, M.; Babar, N.; Noy, N.; Byrd, N.; Roy, N.; Momchev, N.; Chauhan, N.; Sachdeva, N.; Bunyan, O.; Botarda, P.; Caron, P.; Rubenstein, P. K.; Culliton, P.; Schmid, P.; Sessa, P. G.; Xu, P.; Stanczyk, P.; Tafti, P.; Shivanna, R.; Wu, R.; Pan, R.; Rokni, R.; Willoughby, R.; Vallu, R.; Mullins, R.; Jerome, S.; Smoot, S.; Girgin, S.; Iqbal, S.; Reddy, S.; Sheth, S.; Põder, S.; Bhat- nagar, S.; Panyam, S. R.; Eiger, S.; Zhang, S.; Liu, T.; Ya- covone, T.; Liechty, T.; Kalra, U.; Evci, U.; Misra, V.; Rose- berry, V.; Feinberg, V.; Kolesnikov, V.; Han, W.; Kwon, W.; Chen, X.; Chow, Y.; Zhu, Y.; Wei, Z.; Egyed, Z.; Cotruta, V.; Giang, M.; Kirk, P.; Rao, A.; Black, K.; Babar, N.; Lo, J.; Moreira, E.; Martins, L. G.; Sanseviero, O.; Gonzalez, L.; Gleicher, Z.; Warkentin, T.; Mirrokni, V.; Senter, E.; Collins, E.; Barral, J.; Ghahramani, Z.; Hadsell, R.; Matias, Y.; Sculley, D.; Petrov, S.; Fiedel, N.; Shazeer, N.; Vinyals, O.; Dean, J.; Hassabis, D.; Kavukcuoglu, K.; Farabet, C.; Buchatskaya, E.; Alayrac, J.-B.; Anil, R.; Dmitry; Lepikhin; Borgeaud, S.; Bachem, O.; Joulin, A.; Andreev, A.; Hardin, C.; Dadashi, R.; and Hussenot, L. 2025a. Gemma 3 Techni- cal Report. arXiv:2503.19786. · arXiv
- Team, G. V.; Karlinsky, L.; Arbelle, A.; Daniels, A.; Nas- sar, A.; Alfassi, A.; Wu, B.; Schwartz, E.; Joshi, D.; Kondic, J.; Shabtay, N.; Li, P.; Herzig, R.; Abedin, S.; Perek, S.; Harary, S.; Barzelay, U.; Goldfarb, A. R.; Oliva, A.; Wieles, B.; Bhattacharjee, B.; Huang, B.; Auer, C.; Gutfreund, D.; Beymer, D.; Wood, D.; Kuehne, H.; Hansen, J.; Shtok, J.; Wong, K.; Bathen, L. A.; Mishra, M.; Lysak, M.; Dolfi, M.; Yurochkin, M.; Livathinos, N.; Harel, N.; Azulai, O.; Na- parstek, O.; de Lima, R. T.; Panda, R.; Doveh, S.; Gupta, S.; Das, S.; Zawad, S.; Kim, Y.; He, Z.; Brooks, A.; Goodhart, G.; Govindjee, A.; Leist, D.; Ibrahim, I.; Soffer, A.; Cox, D.; Soule, K.; Lastras, L.; Desai, N.; Ofek-koifman, S.; Ragha- van, S.; Syeda-Mahmood, T.; Staar, P.; Drory, T.; and Feris, R. 2025b. Granite Vision: a lightweight, open-source multi- modal model for enterprise Intelligence. arXiv:2502.09927. · arXiv
- van den Berg, L.; Engelsma, T.; and Peute, L. 2024. Explo- ration of Eye-Tracking Methodologies in Usability Testing of Digital Health Technology: A Rapid Review. Studies in health technology and informatics, 316: 1130-1134.
- Wang, J.; Antonenko, P. D.; Celepkolu, M.; Jimenez, Y.; Fieldman, E.; and Fieldman, A. 2019. Exploring Relation- ships Between Eye Tracking and Traditional Usability Test- ing Data. International Journal of Human-Computer Inter- action, 35: 483 -494.
- Wu, J.; Peng, Y.-H.; Li, X. Y. A.; Swearngin, A.; Bigham, J. P.; and Nichols, J. 2024. UIClip: A Data-driven Model for Assessing User Interface Design. In ACM Symposium on User Interface Software and Technology.
- Wu, Q.; Bansal, G.; Zhang, J.; Wu, Y.; Zhang, S.; Zhu, E.; Li, B.; Jiang, L.; Zhang, X.; and Wang, C. 2023a. AutoGen: En- abling Next-Gen LLM Applications via Multi-Agent Con- versation Framework. ArXiv, abs/2308.08155. · arXiv
- Wu, S.; Fei, H.; Qu, L.; Ji, W.; and Chua, T.-S. 2023b. NExT-GPT: Any-to-Any Multimodal LLM. ArXiv, abs/2309.05519. · arXiv
- Xu, P.; Ehinger, K. A.; Zhang, Y.; Finkelstein, A.; Kulka- rni, S. R.; and Xiao, J. 2015. TurkerGaze: Crowdsourc- ing Saliency with Webcam based Eye Tracking. ArXiv, abs/1504.06755. · arXiv
- Zhan, J.; Dai, J.; Ye, J.; Zhou, Y.; Zhang, D.; Liu, Z.; Zhang, X.; Yuan, R.; Zhang, G.; Li, L.; Yan, H.; Fu, J.; Gui, T.; Sun, T.; Jiang, Y.; and Qiu, X. 2024. AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling. ArXiv, abs/2402.12226. · arXiv
Cited by
Sorted by citations
Criticmate: Stagewise Human–AI Co-Critique in Single-Screen UI Evaluation
Ko, J., Choi, J., Morales, C., Kim, D., & Ko, M. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790929 · Cited by 1 · see citing works
- Authors
- Kadegaonkar, M., & Karim, K.
- Affiliations
- Heriot-Watt University (GB)
- ORCID
- Karim, Kayvan
- Venue
- Proceedings of the AAAI Symposium Series
- Published
- 2025-08-01
- Volume
- 6
- Issue
- 1
- Pages
- 244-254
- ISSN
- 2994-4317 (ISSN-L)
- OpenAlex
- W4412841062
- Cited by
- 3
- References
- 0
- Citations by year
- 2026: 3
- FWCI
- 3.07
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Symposium Series (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Physical Sciences › Computer Science › Human-Computer Interaction › Gaze Tracking and Assistive Technology
- Social Sciences › Psychology › Social Psychology › Human-Automation Interaction and Safety
- Keywords
- usability testing, eye tracking, agentic systems, multi-agent systems, user interface evaluation, heuristic evaluation, large language models, gaze analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
