Metraipolis › archive › dc_0518aa2ef5b8

EMBERS: Empirically Motivated Robustness Testing of Deep Research Systems via Defect-Guided Fuzzing — arXiv:2611.03723

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03723
License (as archived)
CC0-1.0
Archived
2026-11-04T18:21:58.892Z
SHA-256 of the archived text
a6e8959cdce8a23ee27258ad706f8216f7e4356ab7aa56b34a111f1967f71c60
Stable URL of this page
https://metraipolis.com/documento/dc_0518aa2ef5b8

How to cite

EMBERS: Empirically Motivated Robustness Testing of Deep Research Systems via Defect-Guided Fuzzing — arXiv:2611.03723 — arXiv (en), https://arxiv.org/abs/2611.03723 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0518aa2ef5b8 (Metraipolis archive dc_0518aa2ef5b8, sha256 a6e8959cdce8a23ee27258ad706f8216f7e4356ab7aa56b34a111f1967f71c60)
BibTeX
@misc{dc0518aa2ef5b8,
  title = {EMBERS: Empirically Motivated Robustness Testing of Deep Research Systems via Defect-Guided Fuzzing — arXiv:2611.03723},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03723},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0518aa2ef5b8; sha256 a6e8959cdce8a23ee27258ad706f8216f7e4356ab7aa56b34a111f1967f71c60},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03723. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep Research (DR) systems extend large language models into autonomous agents that decompose complex information needs, iteratively search the web, and synthesize evidence to answer challenging questions. However, their multi-stage execution may introduce robustness risks, as variations in user questions or intermediate search inputs may propagate across research stages and lead to incorrect answers. Existing evaluations focus on task-solving capabilities or robustness against external evidence disturbances, leaving intrinsic weaknesses in DR execution insufficiently explored. Thus, we conduct an empirical study of 1,932 execution trajectories from three representative DR systems and identify nine recurring defect categories across subquestion formulation, online search, and final reasoning. Guided by these findings, we propose EMBERS, an empirically motivated, defect-guided fuzzing framework for robustness testing of DR systems. Starting from correctly answered seed questions, EMBERS generates stage-targeted test inputs using defect-guided mutation, web-search-assisted fidelity assurance, and diversity-aware seed maintenance. Experiments across 16 framework--model--dataset settings show that EMBERS achieves 3.21 times the failure-discovery throughput of the strongest baseline under identical testing budgets. Human and LLM-assisted evaluations demonstrate that most generated inputs preserve the original information need and necessary contextual constraints. Moreover, model fine-tuning experiments show consistent-answer performance improvement, highlighting their value for robustness testing and model improvement.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.03723 — 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 2026-11-04T18:21:13.488Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).