About this paper
A dynamic stress-testing framework shows that search agents often answer confidently despite unreliable retrieved evidence and may rely on memorized knowledge when documents are factually wrong.
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…
search agentsmulti-step question answeringDeepStressstress-testing frameworkdegraded evidenceretrieval modulesynthetic environmenttrustworthinessrelevancefactuality
- Upvotes
- 4
- Authors
- 3
- Published
- Nov 12, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
DeepStress: Stress-Testing Deep Search Agents was first seen on Hugging Face · Daily papers on Nov 13, 2026. Since then it has appeared in 31 checks on 4 different days. Its best position was #22 of 30, reached on Nov 14, 15:28 UTC. It is #26 right now, slipping from #23 to #26 over the last 6 checks.