---
title: "Visualizing Deep Agents in Long-Horizon Tasks: Towards Explainable and Trustworthy Agentic AI"
authors:
  - "Amirkia Rafiei Oskooei"
  - "Mehmet S. Aktas"
doi: "10.24963/ijcai.2026/987"
url: "https://ijcai.org/proceedings/2026/987"
pdf: "https://ijcai.org/proceedings/2026/0987.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "8492-8496"
track: "Demo Track"
keywords:
  - "AI: Humans and AI"
  - "AI: AI Ethics, Trust, Fairnes"
  - "AI: Agent-based and Multi-agent Systems"
---

# Visualizing Deep Agents in Long-Horizon Tasks: Towards Explainable and Trustworthy Agentic AI

Amirkia Rafiei Oskooei, Mehmet S. Aktas

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 8492-8496. DOI: [10.24963/ijcai.2026/987](https://doi.org/10.24963/ijcai.2026/987)

## 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.