ZekunYao — accepted AI-conference papers

2026

A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research

Zhuofan Shi, Ming Ma, ZekunYao, Fangkai Yang, Jue Zhang, Dongge Han +4

ICML 2026poster

Open-Ended Deep Research (OEDR) pushes LLM agents beyond short-form QA toward long-horizon workflows that iteratively search, connect, and synthesize evidence into structured reports. However, existing OEDR agents largely follow either linear "search-then-generate" accumulation or outline-centric pl…

Cited by 1 Source ↗Scholar ↗

2025

Training Large Language Models for Retrieval-Augmented Question Answering through Backtracking Correction

Huawen Feng, ZekunYao, Junhao Zheng, Qianli Ma

ICLR 2025poster

Despite recent progress in Retrieval-Augmented Generation (RAG) achieved by large language models (LLMs), retrievers often recall uncorrelated documents, regarded as "noise" during subsequent text generation. To address this, some methods train LLMs to distinguish between relevant and irrelevant doc…

Cited by 0 Source ↗PDF ↗Scholar ↗