Metraipolis › archive › dc_a4fec166fa26

From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis — arXiv:2609.32514

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.32514
License (as archived): CC0-1.0
Archived: 2026-10-07T20:55:36.988Z
SHA-256 of the archived text: 7841531de898fe98b2444b1ec0f6a6244d68f37429e833a9b1bf50470b0ec521
Stable URL of this page: https://metraipolis.com/documento/dc_a4fec166fa26

How to cite

From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis — arXiv:2609.32514 — arXiv (en), https://arxiv.org/abs/2609.32514 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4fec166fa26 (Metraipolis archive dc_a4fec166fa26, sha256 7841531de898fe98b2444b1ec0f6a6244d68f37429e833a9b1bf50470b0ec521)

BibTeX

@misc{dca4fec166fa26,
  title = {From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis — arXiv:2609.32514},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32514},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4fec166fa26; sha256 7841531de898fe98b2444b1ec0f6a6244d68f37429e833a9b1bf50470b0ec521},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32514. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-driven agents are increasingly deployed in complex applications, where long agentic traces make failures difficult to diagnose. Existing trace diagnosis methods often conflate anomalies, errors, and failures, making diagnostic targets ambiguous; they also lack structured modeling of how causally relevant errors propagate and amplify into final task failures, resulting in unreliable failure attribution. To address these problems, we propose CEG-Agent, a tool-augmented agentic framework for causal diagnosis of agentic traces. Specifically, CEG-Agent introduces an explicit taxonomy of anomalies, errors, and failures, and constructs Causal Error Graphs (CEGs), a unified typed representation that links execution events, diagnostic nodes, and failure outcomes through causal relations. To evaluate causal trace diagnosis, we further construct CEG-Bench, a fully agent-annotated benchmark with high-confidence, consensus-derived CEG annotations obtained through an Adversarial Agentic Adjudication Protocol (AAAP). We validate the resulting annotations against an expert-curated human gold set, which shows close agreement with the automatic annotations. Experiments on CEG-Bench demonstrate that CEG-Agent achieves state-of-the-art performance under both semantically relaxed and structurally exact evaluation criteria. Our code is publicly available.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.32514 — 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 2026-10-07T20:29:00.841Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).