Jul 2026· International Conference on the Theory of Information Retrieval· pp. 34-43· 3 citations· 51 references
Computer Science
TL;DR
The sandbox provides a search API that indexes large-scale public web corpora, namely ClueWeb22 and FineWeb, using a state-of-the-art dense retriever and approximate nearest neighbor search via DiskANN and achieves comparable latency to popular commercial APIs while ensuring stable document rankings across runs.
Abstract
Deep research systems represent an emerging class of agentic information retrieval methods that generate comprehensive and well-supported reports to complex queries, and/or answers to hard-to-locate factual questions. However, most existing systems rely on dynamic commercial search APIs, which pose reproducibility and transparency challenges, in addition to high costs. To address these limitations, we introduce DeepResearchGym as a free and open-source search sandbox for reproducible research on deep research systems. The sandbox provides a search API that indexes large-scale public web corpora, namely ClueWeb22 and FineWeb, using a state-of-the-art dense retriever and approximate nearest neighbor search via DiskANN. It achieves comparable latency to popular commercial APIs while ensuring stable document rankings across runs. We demonstrate the sandbox's utility through two use cases. For training, we synthesize queries grounded in the indexed corpora and show that search agents trained within the sandbox generalize to commercial search at inference time, enabling cost-effective reinforcement learning. For evaluation, we extend the Researchy Questions benchmark with LLM-as-a-judge metrics to measure alignment with users' information needs, retrieval faithfulness, and report quality. Evaluation results show that system rankings remain consistent when switching from commercial APIs to ours.
While autonomous agents have made significant strides in"deep research"by iteratively navigating the open web to synthesize information, real-world problem-solving is rarely confined to a single environment. Complex analytical tasks inherently require agents to weave together evidence from both ambiguous unstructured text (e.g., the open web) and highly precise structured data (e.g., relational databases). However, existing benchmarks evaluate these modalities in isolation, failing to capture the critical"handoff"- the ability to preserve constraints when moving evidence between systems. We introduce HybridDeepResearch, to our knowledge the first deep-research benchmark that requires both web search and SQL to form a complete, verifiable answer. The benchmark contains 380 tool-dependent tasks grounded in LiveSQLBench-Base-Lite databases and public web corpora, validated through automated checks and human review, and covering three reasoning patterns: SQL2S, S2SQL, and Parallel. Evaluations across proprietary and open-weight models under various agentic scaffolds reveal that even state-of-the-art models like GLM-5.2, Claude-Sonnet-4.6 and GPT-5 achieve only about 50-54% Pass@8 on the hard subset. Notably, results show that directional reasoning is substantially more difficult than parallel intersection, highlighting that bridging structured and unstructured information spaces without losing constraints remains a major open challenge for agentic systems. Code and datasets are publicly available at GitHub (https://github.com/Snowflake-AI-Research/HybridDeepResearch) and Hugging Face (https://huggingface.co/datasets/Snowflake/HybridDeepResearch).
Ruofan Wu, Peiran Xu, Xiaolong Li et al.· 0 citations
This work introduces a verifiable benchmark of 500 deep research tasks spanning 31 topics and 10 major categories, with three query forms designed to probe complementary capabilities required for deep research.
Can Wang, Haoran Chen, Hao Gao et al.· 0 citations
WANDR (Wide ANd Deep Research) is a benchmark of 500 realistic, challenging data-collection tasks for research agents. Each task requires a system to discover a large set of entities that satisfy specified criteria (breadth), investigate each entity through multiple coordinated web searches (depth), and return independently verifiable records with supporting sources and excerpts. Tasks are represented as qualification key hierarchies that specify the entities, relationships, evidence, and required count at each level; a hierarchy with n companies, m employees per company, and k sources per employee requires n x m x k records. This structure supports diverse workflows such as market mapping, due diligence, literature review, product comparison, and talent sourcing, with targets ranging from dozens to thousands of records. WANDR replaces static gold answer sets with task-specific judges that refetch cited pages and verify each record against its evidence, allowing evaluation of current and changing facts. Record verdicts are aggregated into soft and hard precision, recall, and F1 scores that distinguish factual quality, coverage, and hierarchical completeness. The tasks are derived from de-identified product-usage logs and produced through a semi-automated pipeline with automated checks, empirical audits, and human review where needed. We evaluate six production research systems and find that the benchmark is far from saturated: at high effort, the strongest system reaches only 0.363 soft F1 and 0.133 hard F1. Performance degrades as target volume and hierarchy depth increase, with incomplete discovery, missing enrichment, and incomplete evidence construction remaining major bottlenecks. The benchmark and evaluation harness are available at https://github.com/perplexityai/wandr.
Vitaliy Polshkov, Marcin Pitera, Jeremy Yang et al.· 1 citation
Deep Research Pretraining (DRP), an offline framework that derives predictive navigation supervision from naturally occurring evidence structures, is introduced, an offline framework that derives predictive navigation supervision from naturally occurring evidence structures.
Jiang-Nan Zhou, Zhi-Yuan Fan, Xing Wu et al.· 1 citation
A taxonomy of core techniques, a layered system architecture and architectural paradigms, reviews representative implementations and applications, and highlights open challenges and future directions are provided.
Jinyan Cai· International journal of eng...· 0 citations
