Visualizing Deep Agents in Long-Horizon Tasks: Towards Explainable and Trustworthy Agentic AI
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Demo Track. Pages 8492-8496.
https://doi.org/10.24963/ijcai.2026/987
Keywords
- AI: Humans and AI
- AI: AI Ethics, Trust, Fairnes
- AI: Agent-based and Multi-agent Systems
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.
@inproceedings{ijcai2026p987,
title = {Visualizing Deep Agents in Long-Horizon Tasks: Towards Explainable and Trustworthy Agentic AI},
author = {Rafiei Oskooei, Amirkia and Aktas, Mehmet S.},
booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-26}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Diego Calvanese},
pages = {8492--8496},
year = {2026},
month = {8},
note = {Demo Track},
doi = {10.24963/ijcai.2026/987},
url = {https://doi.org/10.24963/ijcai.2026/987},
}
TY - CPAPER TI - Visualizing Deep Agents in Long-Horizon Tasks: Towards Explainable and Trustworthy Agentic AI AU - Rafiei Oskooei, Amirkia AU - Aktas, Mehmet S. T2 - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2026 SP - 8492 EP - 8496 DO - 10.24963/ijcai.2026/987 UR - https://doi.org/10.24963/ijcai.2026/987 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
