WebExpert: domain-aware web agents with critic-guided expert experience for high-precision search

TL;DR

WebExpert is a domain-aware web agent that enhances high-precision search in specialized fields through experience retrieval, facet induction, and preference-optimized planning, achieving significant accuracy improvements.

Contribution

The paper introduces WebExpert, a novel end-to-end web agent with dynamic facet induction and preference-based planning, advancing domain-specific web search capabilities.

Findings

WebExpert improves Answer EM by 1.5-3.6 percentage points over baselines.

It reduces page hops, indicating more efficient retrieval.

Ablation studies confirm the effectiveness of each component.

Abstract

Specialized web tasks in finance, biomedicine, and pharmaceuticals remain challenging due to missing domain priors: queries drift, evidence is noisy, and reasoning is brittle. We present WebExpert, a domain-aware web agent that we implement end-to-end, featuring : (i) sentence-level experience retrieval with topic merging and rule distillation, (ii) schemalight facet induction that bootstraps time,region,policy,industry facets from weak supervision instead of static hand-written lexicons, and (iii) preference-optimized planning that jointly improves query planning and retrieval via pairwise preference learning alongside a coverage-aware objective. At inference, a lightweight experience gate biases decoding toward active facets with fallback under low-retrieval confidence. On GAIA, GPQA, HLE, and WebWalkerQA, WebExpert improves Answer Exact Match (EM) by 1.5-3.6 pp over the strongest browsing baseline and reduces page hops. Analysis shows consistent gains and ablations on retrieval, topic merging, facet induction, and preference-aware training.