Metraipolis › archive › dc_642a393a032c

Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems — arXiv:2608.29646

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29646
License (as archived)
CC0-1.0
Archived
2026-10-17T07:41:00.920Z
SHA-256 of the archived text
8a3f55db45789ec25565ae8749daa3cb6f618ccafa1d77d9f182bcbf47e10a9c
Stable URL of this page
https://metraipolis.com/documento/dc_642a393a032c

How to cite

Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems — arXiv:2608.29646 — arXiv (en), https://arxiv.org/abs/2608.29646 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_642a393a032c (Metraipolis archive dc_642a393a032c, sha256 8a3f55db45789ec25565ae8749daa3cb6f618ccafa1d77d9f182bcbf47e10a9c)
BibTeX
@misc{dc642a393a032c,
  title = {Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems — arXiv:2608.29646},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29646},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_642a393a032c; sha256 8a3f55db45789ec25565ae8749daa3cb6f618ccafa1d77d9f182bcbf47e10a9c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29646. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable to execution failures. Accurate failure attribution is therefore critical for improving agent reliability. Existing topology- and spectrum-based methods exploit trajectory structures but often overlook fine-grained semantics, while LLM-based attribution methods capture semantic cues but suffer from long-context degradation over lengthy trajectories. To address these challenges, we propose DUOTRACE, a plug-and-play detection filter for LLM-based failure attribution. DUOTRACE follows a detect-before-attribute paradigm: it first detects anomalous executions and then supplies focused trajectory evidence to downstream LLM-based attribution methods. For effective VAE-based anomaly detection on agent trajectories, DUOTRACE integrates dual-view semantic-structural node representations, a Tree-LSTM-based trajectory encoder, and prefix-chain- and LLM-based data augmentation to handle heterogeneous nodes, hierarchical execution structures, and limited failure data. Experiments with six LLM-based attribution baselines show that DUOTRACE improves agent-level and step-level attribution accuracy by 8.7% and 7.0%, respectively.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.29646 — 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 2026-10-17T07:27:42.007Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).