Paper Detail
Ismael Rousseau, Geraldine Damnati, Frederic Bechet
While search agents demonstrate impressive capabilities in multi-step question answering, their robustness to poor-quality evidence remains under-explored. Such evidence is rare in benchmark corpora, and resulting failures are hard to reproduce. We propose DeepStress, a dynamic stress-testing framework that subjects agents to degraded evidence at controlled rates. It replaces the retrieval module with a synthetic environment where documents are generated dynamically for each query, under independent control of their trustworthiness, relevance, and factuality. To characterize behavior under stress, we go beyond binary accuracy with a five-way classification of final-answer outcomes and two new reliability-aware metrics, RAS and CoPRAS, which credit cautious behavior and account for computational cost. Evaluating 12 systems on questions from HotpotQA and BrowseComp-Plus, we find that several open-weight agents answer confidently when sources contain obvious credibility red flags, and that many HotpotQA questions are answered from parametric knowledge even when all returned documents are factually wrong.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{rousseau2026deepstress,
title = {DeepStress: Stress-Testing Deep Search Agents},
author = {Ismael Rousseau and Geraldine Damnati and Frederic Bechet},
year = {2026},
abstract = {While search agents demonstrate impressive capabilities in multi-step question answering, their robustness to poor-quality evidence remains under-explored. Such evidence is rare in benchmark corpora, and resulting failures are hard to reproduce. We propose DeepStress, a dynamic stress-testing framework that subjects agents to degraded evidence at controlled rates. It replaces the retrieval module with a synthetic environment where documents are generated dynamically for each query, under indepen},
url = {https://huggingface.co/papers/2607.13920},
keywords = {search agents, multi-step question answering, DeepStress, stress-testing framework, degraded evidence, retrieval module, synthetic environment, trustworthiness, relevance, factuality, five-way classification, reliability-aware metrics, RAS, CoPRAS, open-weight agents, HotpotQA, BrowseComp-Plus, parametric knowledge, huggingface daily},
eprint = {2607.13920},
archiveprefix = {arXiv},
}
{}