ORCA: ORchestrating Causal Agent
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912971643420672 |
|---|---|
| author | Chung, Joanie Hayoun Lee, Sumin Lim, Sungbin |
| author_facet | Chung, Joanie Hayoun Lee, Sumin Lim, Sungbin |
| contents | Causal analysis on relational databases is challenging, as analysis datasets must be repeatedly queried from complex schemas. Recent LLM systems can automate individual steps, but they hardly manage dependencies across analysis stages, making it difficult to preserve consistency between causal hypothesis. We propose ORCA (ORchestrating Causal Agent), an interactive multi-agent framework to enable coherent causal analysis on relational databases by maintaining shared state and introducing human checkpoints. In a controlled user study, participants using ORCA successfully completed end-to-end analysis more often than with a baseline LLM (GPT-4o-mini) assistant by 42 percentage points, achieved substantially lower ATE error, and reduced time spent on repetitive data exploration and query refinement by 76\% on average. These results show that ORCA improves both how users interact with the causal analysis pipeline and the reliability of the resulting causal conclusions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_21304 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ORCA: ORchestrating Causal Agent Chung, Joanie Hayoun Lee, Sumin Lim, Sungbin Databases Multiagent Systems Causal analysis on relational databases is challenging, as analysis datasets must be repeatedly queried from complex schemas. Recent LLM systems can automate individual steps, but they hardly manage dependencies across analysis stages, making it difficult to preserve consistency between causal hypothesis. We propose ORCA (ORchestrating Causal Agent), an interactive multi-agent framework to enable coherent causal analysis on relational databases by maintaining shared state and introducing human checkpoints. In a controlled user study, participants using ORCA successfully completed end-to-end analysis more often than with a baseline LLM (GPT-4o-mini) assistant by 42 percentage points, achieved substantially lower ATE error, and reduced time spent on repetitive data exploration and query refinement by 76\% on average. These results show that ORCA improves both how users interact with the causal analysis pipeline and the reliability of the resulting causal conclusions. |
| title | ORCA: ORchestrating Causal Agent |
| topic | Databases Multiagent Systems |
| url | https://arxiv.org/abs/2508.21304 |