Visualizing Deep Agents in Long-Horizon Tasks: Towards Explainable and Trustworthy Agentic AI
Amirkia Rafiei Oskooei, Mehmet S. Aktas
Abstract
The transition from prompt-based Large Language Models (LLMs) to autonomous Deep Agents has enabled the automation of long-horizon tasks. However, as these agents adopt hierarchical architectures with nested tool usage, they suffer from significant opacity. Existing linear tracing tools fail to capture the multi-dimensional complexity of parallel sub-agent execution, hindering both debugging and user trust. We propose a general-purpose observability framework that decomposes agent execution into four distinct visualization dimensions: Temporal, Cognitive, Hierarchical, and Spatial. We validate this framework through RepoLearn, an open-source workbench for automated codebase comprehension. Our user study demonstrates that this multi-dimensional approach reduces the Time-to-Insight (TTI) for complex behavioral analysis by 56% and significantly lowers cognitive load (NASA-TLX) compared to state-of-the-art linear traces. The source code is available at https://github.com/amirkiarafiei/repo-learn and the demo at https://www.youtube.com/watch?v=s3U6E9o94gk.
BibTeX
@inproceedings{ijcai2026_visualizingdeepa,
title = {Visualizing Deep Agents in Long-Horizon Tasks: Towards Explainable and Trustworthy Agentic AI},
author = {Amirkia Rafiei Oskooei and Mehmet S. Aktas},
booktitle = {IJCAI 2026},
year = {2026}
}