EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
2026-04-09 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed Q+, a set of tools that helps AI agents search the web more carefully and organize information better when answering complex questions. They combined Q+ with Eigent, an open-source system that uses multiple AI helpers to get things done on computers. Testing on several benchmarks showed that Q+ improved the accuracy of Eigent's web search for different AI models. Their examples also suggest that Q+ helps the AI plan searches more clearly and handle evidence in a more understandable way.
AI agentsweb searchquery planningevidence aggregationmulti-agent systemsbenchmarkslanguage modelsEigentinformation retrievaltool-calling trajectories
Authors
Boer Zhang, Mingyan Wu, Dongzhuoran Zhou, Yuqicheng Zhu, Wendong Fan, Puzhen Zhang, Zifeng Ding, Guohao Li, Yuan He
Abstract
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.