Organizations: Meta · Northeastern University, China · University of Oslo · Bosch Center for AI · University of Stuttgart · University of Cambridge · Mina AI · Amazon
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 XBench 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.
Figures & tables
Figure 1. System architecture of the Eigent multi-agent framework and the EigentSearch-Q+ enhancement. (a) High-level architectural overview of Eigent . (b) Detailed schematic of the Browser Agent, and added Q+ tools. System architecture diagram showing (a) the high-level \eigentmulti-agent framework and (b) the Browser Agent with additional \qplustools for query processing, targeted extraction, and research progress reflection.
Figure 2. Performance analysis of agent configurations across four LLM backends. Accuracy results for GPT-4.1 mini (a), GPT-4.1 (b), GPT-5.1 (c), and Minimax M2.5 (d) across four datasets. The Q+ framework is evaluated against Direct Generation (Baseline), Search Only, and Eigent browser agent. A four-panel benchmark figure comparing accuracy across four datasets for GPT-4.1 mini, GPT-4.1, GPT-5.1, and Minimax M2.5. In most panels, \qplusoutperforms the baseline, Search Only, and the standard \eigentbrowser agent, with the largest gains on stronger GPT backends.
SimpleQA-Verified
FRAMES
WebWalkerQA
XBench
Weighted Avg.
GPT-4.1 mini
0.8
-0.8
-0.6
4.0
0.1
GPT-4.1
2.3
0.6
5.6
12.0
3.0
GPT-5.1
1.5
5.7
4.4
8.0
3.8
Minimax M2.5
0.8
1.3
-1.5
7.0
0.6
Table 1. Accuracy improvements of EigentSearch-Q+ over the Eigent browser agent. All values are reported in percentage points (pp) and represent the accuracy change of Q+ relative to Eigent (negative values indicate decreases). The weighted average summarizes the overall performance gain across all evaluated benchmarks.