DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918324273676288 |
|---|---|
| author | Sheng, Rui Yang, Yukun Shi, Chuhan Lin, Yanna Chen, Zixin Qu, Huamin Cheng, Furui |
| author_facet | Sheng, Rui Yang, Yukun Shi, Chuhan Lin, Yanna Chen, Zixin Qu, Huamin Cheng, Furui |
| contents | Large language model (LLM)-based multi-agent systems have demonstrated impressive capabilities in handling complex tasks. However, the complexity of agentic behaviors makes these systems difficult to understand. When failures occur, developers often struggle to identify root causes and to determine actionable paths for improvement. Traditional methods that rely on inspecting raw log records are inefficient, given both the large volume and complexity of data. To address this challenge, we propose a framework and an interactive system, DiLLS, designed to reveal and structure the behaviors of multi-agent systems. The key idea is to organize information across three levels of query completion: activities, actions, and operations. By probing the multi-agent system through natural language, DiLLS derives and organizes information about planning and execution into a structured, multi-layered summary. Through a user study, we show that DiLLS significantly improves developers' effectiveness and efficiency in identifying, diagnosing, and understanding failures in LLM-based multi-agent systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05446 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors Sheng, Rui Yang, Yukun Shi, Chuhan Lin, Yanna Chen, Zixin Qu, Huamin Cheng, Furui Human-Computer Interaction Large language model (LLM)-based multi-agent systems have demonstrated impressive capabilities in handling complex tasks. However, the complexity of agentic behaviors makes these systems difficult to understand. When failures occur, developers often struggle to identify root causes and to determine actionable paths for improvement. Traditional methods that rely on inspecting raw log records are inefficient, given both the large volume and complexity of data. To address this challenge, we propose a framework and an interactive system, DiLLS, designed to reveal and structure the behaviors of multi-agent systems. The key idea is to organize information across three levels of query completion: activities, actions, and operations. By probing the multi-agent system through natural language, DiLLS derives and organizes information about planning and execution into a structured, multi-layered summary. Through a user study, we show that DiLLS significantly improves developers' effectiveness and efficiency in identifying, diagnosing, and understanding failures in LLM-based multi-agent systems. |
| title | DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2602.05446 |