Metraipolis › archive › dc_28a2679869ee

EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems — arXiv:2609.01360

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01360
License (as archived)
CC0-1.0
Archived
2026-10-17T06:32:27.845Z
SHA-256 of the archived text
be0d7b3f39b27856321f196ad50a4c9a4e6cbe1bd39d54a23540bca874301d40
Stable URL of this page
https://metraipolis.com/documento/dc_28a2679869ee

How to cite

EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems — arXiv:2609.01360 — arXiv (en), https://arxiv.org/abs/2609.01360 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28a2679869ee (Metraipolis archive dc_28a2679869ee, sha256 be0d7b3f39b27856321f196ad50a4c9a4e6cbe1bd39d54a23540bca874301d40)
BibTeX
@misc{dc28a2679869ee,
  title = {EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems — arXiv:2609.01360},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01360},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28a2679869ee; sha256 be0d7b3f39b27856321f196ad50a4c9a4e6cbe1bd39d54a23540bca874301d40},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01360. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agent failures often contain multiple related errors rather than a single mistake. Existing attribution methods usually identify a responsible agent, step, or root cause, but do not explicitly model dependency between errors. We introduce EDGE, an Error Dependency Graph-guided multi-Error attribution framework. EDGE constructs an error dependency graph from observed error events and validates a reliable causal subset through counterfactual rollout. The inference graph guides a two-stage LLM-as-judge detector for error attribution, and the intervention-validated subgraph provides a more reliable basis for explanation and repair analysis. Experiments on TRAIL and MAST show that EDGE improves category-level multi-error attribution across most evaluated models and settings. Experiments with adapted Who&When-style prompts show that the graph helps across prompting strategies. These results suggest that dependency structure is a useful diagnostic prior for agent failures beyond isolated root-cause prediction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01360 — 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 2026-10-17T06:15:12.692Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).