Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety

ACL ARR 2026 January Submission6970 Authors

Keywords: Agent, Large Language Model, Guardrail, Deep Research, Open-domain Evaluation

Abstract:

Deep research frameworks have shown promising capabilities in synthesizing comprehensive reports from web sources. While deep research possesses significant potential to address complex issues through planning and research cycles, existing frameworks are deficient in sufficient evaluation procedures and stage-specific protections.
They typically treat evaluation as exact match accuracy of question-answering, but overlook crucial aspects of report quality such as *credibility*, *coherence*, *breadth*, *depth*, and *safety*.
This oversight may result in hazardous or malicious sources being integrated into the final report. To address this, we introduce **DeepResearchGuard**, a framework featuring four-stage safeguards with open-domain evaluation, and **DRSafeBench**, a novel stage-wise safety benchmark. Evaluating across *GPT-4o*, *o4-mini*, *Gemini-2.5-flash*, *DeepSeek-v3*, *GPT-5*, DeepResearchGuard improves defense success rates by **16.53%** while reducing over-refusal to **6%**. Through extensive experiments, we show that DeepResearchGuard enables comprehensive open-domain evaluation and stage-aware defenses that effectively block harmful content propagation, while systematically improving report quality without excessive over-refusal rates.

Paper Type: Long

Research Area: Safety and Alignment in LLMs

Research Area Keywords: Agent, Large Language Model, Guardrail, Deep Research, Open-domain Evaluation

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English

Submission Number: 6970