collaborators

7 papers

cs.AI2026

Agentic Retrieval-Augmented Generation for Financial Document Question Answering

Yang Shu, Yingmin Liu, Zequn Xie

Financial document question answering (QA) demands complex multi-step numerical reasoning over heterogeneous evidence--structured tables, textual narratives, and footnotes--scatter…

cs.LG2026

SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating

Zequn Xie, Junjie Wang, Dan Yang +4

Deep research agents have demonstrated remarkable capabilities in complex information-seeking tasks, yet this power comes at a steep computational cost. Driven by accuracy-focused…

cs.AI2026

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning

Junjie Wang, Zequn Xie, Dan Yang +9

Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency remains underexplored. We observe th…

cs.CL2026

Mitigating Hallucination on Hallucination in RAG via Ensemble Voting

Zequn Xie, Zhengyang Sun

Retrieval-Augmented Generation (RAG) aims to reduce hallucinations in Large Language Models (LLMs) by integrating external knowledge. However, RAG introduces a critical challenge:…

cs.AI2026

PeopleSearchBench: A Multi-Dimensional Benchmark for Evaluating AI-Powered People Search Platforms

Wei Wang, Tianyu Shi, Shuai Zhang +9

AI-powered people search platforms are increasingly used in recruiting, sales prospecting, and professional networking, yet no widely accepted benchmark exists for evaluating their…

cs.CV2026

Dynamic Uncertainty Learning with Noisy Correspondence for Text-Based Person Search

Zequn Xie, Haoming Ji, Chengxuan Li +1

Text-to-image person search aims to identify an individual based on a text description. To reduce data collection costs, large-scale text-image datasets are created from co-occurre…