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

2026-02-03 · Yuelin Hu, Zhengxue Cheng, Ronghua Wu, Qunshan Gu, Hongwei Hu, Wei Liu, Qiao Liang, Li Song 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.

📄 PDF Abstract BibTeX arXiv:2604.06177

Code (0)

등록된 구현이 없습니다.

What's Hidden Matters: Identifying Planning-Critical Occluded Agents using Vision-Language Models

2026-07-01 · Amirhosein Chahe, Tyler Naes, Jovin D'sa, Faizan M. Tariq 외 arxiv

Autonomous vehicles must safely navigate complex environments where planning-critical agents may be hidden from view. Current approaches often treat all occlusions with uniform conservatism, yielding needlessly defensive…

Autonomous Vehicles Autonomous Driving

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

2026-06-11 · Chejian Xu, Zhaorun Chen, Jingyang Zhang, Freddy Lecue 외 arxiv

Hierarchical multi-agent systems (MAS) are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and security are inherently distributed across …

HyDRA: Hybrid Domain-Aware Robust Architecture for Heterogeneous Collaborative Perception

2026-03-25 · Minwoo Song, Minhee Kang, Heejin Ahn arxiv

In collaborative perception, an agent's performance can be degraded by heterogeneity arising from differences in model architecture or training data distributions. To address this challenge, we propose HyDRA (Hybrid Doma…

Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching

2026-04-13 · Rongzhe Wei, Ge Shi, Min Cheng, Na Zhang 외 arxiv

Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massive tool libraries remains challenging du…

Computational Efficiency

A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs

2026-06-02 · Cuong Vuong Tuan, Trang Mai Xuan, Tien-Cuong Nguyen, Vu-Duc Ngo 외 arxiv

Multi-Document Summarization (MDS) plays a critical role in distilling essential information from collections of textual data. Existing approaches often struggle to capture complex inter-document relationships, rely heav…

Multi-Document Summarization Knowledge Graphs