EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
Boer Zhang (Meta), Mingyan Wu (Northeastern University, China), Dongzhuoran Zhou (University of Oslo & Bosch Center of AI), Yuqicheng Zhu (University of Stuttgart & Bosch Center of AI), Wendong Fan (CAMEL-AI.org & Eigent.ai), Puzhen Zhang (CAMEL-AI.org & Eigent.ai), Zifeng Ding (University of Cambridge & Mina AI), Guohao Li (CAMEL-AI.org & Eigent.ai), Yuan He (Amazon)
Architectural Patterns & Composition
Summary
A set of structured query and evidence processing tools that make web search more deliberate for deep research agents, improving accuracy across four benchmarks.
Description
Deep research requires reasoning over web evidence to answer open-ended questions, and it is a core capability for AI agents. Yet many deep research agents still rely on implicit, unstructured search behavior that causes redundant exploration and brittle evidence aggregation. Motivated by Anthropic's "think" tool paradigm and insights from the information-retrieval literature, we introduce Q+, a set of query and evidence processing tools that make web search more deliberate by guiding query planning, monitoring search progress, and extracting evidence from long web snapshots. We integrate Q+ into the browser sub-agent of Eigent, an open-source, production-ready multi-agent workforce for computer use, yielding EigentSearch-Q+. Across four benchmarks (SimpleQA-Verified, FRAMES, WebWalkerQA, and X-Bench DeepSearch), Q+ improves Eigent's browser agent benchmark-size-weighted average accuracy by 3.0, 3.8, and 0.6 percentage points (pp) for GPT-4.1, GPT-5.1, and Minimax M2.5 model backends, respectively. Case studies further suggest that EigentSearch-Q+ produces more coherent tool-calling trajectories by making search progress and evidence handling explicit.
