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

arXiv 2604.06177 ↗First posted 3 Feb 2026cs.IR cs.AI cs.CLcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 10 of its 23 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

10 of 23 references.

References · 10

2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
2017Billion-scale similarity search with GPUscited by 2,477
2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
2021Improving language models by retrieving from trillions of tokenscited by 1,278
2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way