R e T race : Interactive Visualizations for Reasoning Traces of Large Reasoning Models
Computer Graphics Forum · 11.06.2026
DOI: 10.1111/cgf.70452 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 11.06.2026. Verfasst von L. Felder und 4 weiteren Autor:innen. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Recent advances in Large Language Models have led to Large Reasoning Models, which produce step‐by‐step reasoning traces. Such traces may offer insight into how models think, improving explainability and clarifying the underlying process. These traces, however, are often verbose and complex, making them cognitively demanding to comprehend. With this in mind, we propose R e T race , an interactive system that structures and visualizes textual reasoning traces to support understanding. We use a validated reasoning taxonomy to produce structured reasoning data and investigate two types of interactive visualizations thereof. In a controlled human‐subject study, the visualizations provided more accurate comprehension of the model's reasoning and less perceived effort than a raw text baseline. The results of this study could have design implications for making long and complex machine‐generated reasoning processes more usable and transparent, an important step in AI explainability.
Zitieren
APA
Felder, L., Miller, J., Wallinger, M., Kobourov, S. G., & Chen, C. (2026). R e T race : Interactive Visualizations for Reasoning Traces of Large Reasoning Models. Computer Graphics Forum. https://doi.org/10.1111/cgf.70452
Vancouver
Felder L, Miller J, Wallinger M, Kobourov SG, Chen C. R e T race : Interactive Visualizations for Reasoning Traces of Large Reasoning Models. Computer Graphics Forum. 2026. doi:10.1111/cgf.70452
BibTeX
@article{Felder2026,
author = {Felder, L. and Miller, J. and Wallinger, M. and Kobourov, S. G. and Chen, C.},
title = {R e T race : Interactive Visualizations for Reasoning Traces of Large Reasoning Models},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70452}
}
EUVIMED