Metraipolis › archive › dc_69fd4bd44ce0

Rethinking Tool Design for Agentic RCA: A Controlled Empirical Study — arXiv:2610.05009

Source
arXiv
Original
https://arxiv.org/abs/2610.05009
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:41.060Z
SHA-256 of the archived text
e1c04e90ede900f3b9d853a0c31d1ab4b53490765ef39559503fcf099041e8ef
Stable URL of this page
https://metraipolis.com/documento/dc_69fd4bd44ce0

How to cite

Rethinking Tool Design for Agentic RCA: A Controlled Empirical Study — arXiv:2610.05009 — arXiv, https://arxiv.org/abs/2610.05009 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69fd4bd44ce0 (Metraipolis archive dc_69fd4bd44ce0, sha256 e1c04e90ede900f3b9d853a0c31d1ab4b53490765ef39559503fcf099041e8ef)
BibTeX
@misc{dc69fd4bd44ce0,
  title = {Rethinking Tool Design for Agentic RCA: A Controlled Empirical Study — arXiv:2610.05009},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05009},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69fd4bd44ce0; sha256 e1c04e90ede900f3b9d853a0c31d1ab4b53490765ef39559503fcf099041e8ef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05009. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agents are increasingly explored for root cause analysis (RCA) in microservice systems, yet empirical guidance on how to design and combine their tools remains limited. We conduct a controlled empirical study of tool abstraction and composition across models and microservice environments. We implement 24 structured tools for metric access (L1), evidence analysis (L2), and diagnosis (L3), alongside a Python-based reference setting (L0). Using 375 failure cases from three microservice systems, we evaluate eight configurations with Qwen3.7-Plus and compare four Qwen models on a shared subset of four configurations. Our results show that tool configurations affect root cause localization and failure type identification differently. With Qwen3.7-Plus, L3 achieves 82.8% top-1 localization accuracy compared with 85.4% for L0, while requiring less than half the time per case. Adding tool levels can improve type identification while reducing localization accuracy. Trajectory analysis reveals cases in which agents override correct diagnostic recommendations after consulting additional evidence. Model choice also changes tool benefits: adding L3 to L1+L2 improves diagnosis for three models but hurts Qwen3-8B, which rarely invokes L3. Tool configuration rankings further change across microservice systems. These findings provide an empirical foundation for designing and using RCA tools, guiding tool selection and composition according to the model, diagnostic objective, and target system.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.05009 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:27:20.398Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).