Publications

Figure 4 · Multi-agent forecasting frameworkView figure ↗
Figure 4 · Multi-agent forecasting framework · Source
EMNLP 2026 · Main Conference · Oral2026

Agentic Time Machine as an Infrastructure for Future-Event Forecasting

Co-authored by Zihang Zhou · 8 authors

Jingyi Chai, Bingyang Zheng, Xiangrui Liu, Hao Lu, Zihang Zhou, Tianchen Wang, Kemeng Zhang, Siheng Chen

A time-aware evaluation infrastructure for forecasting agents, with a planner–solver–aggregator framework for gathering evidence and producing forecasts.

Figure 2 · SetupX system overviewView figure ↗
Figure 2 · SetupX system overview · Source
Under review · ICLR 2027First author2026

SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?

Zihang Zhou et al. · 10 authors

Zihang Zhou, Ziqian Ren, Yukai Wu, Yingjie Xiong, Wei Zhou, Chao Peng, Dong Zhang, Bingheng Yan, Xuanhe Zhou, Fan Wu

Experience-driven repository setup with reusable XPU knowledge, speculative execution and rollback, and a prosecutor–judge verification protocol.

Figure 2 · Workspace-Bench overviewView figure ↗
Figure 2 · Workspace-Bench overview · Source
NeurIPS 2026 · Poster2026

Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies

Co-authored by Zihang Zhou · 22 authors

Zirui Tang, Xuanhe Zhou, Yumou Liu, Linchun Li, Yukai Wu, Weizheng Wang, Hongzhang Huang, Wei Zhou, Jun Zhou, Jiachen Song, Shaoli Yu, Jinqi Wang, Zihang Zhou, Hongyi Zhou, Yuting Lv, Jinyang Li, Jiashuo Liu, Ruoyu Chen, Chunwei Liu, Guoliang Li, Jihua Kang, Fan Wu

Evaluating agents on realistic workspaces that require reasoning across large-scale file dependencies, with task-specific dependency graphs and rubric-based assessment.

Figure 2 · Technical overview of the surveyView figure ↗
Figure 2 · Technical overview of the survey · Source
Under review · IEEE TKDE2025

LLM/Agent-as-Data-Analyst: A Survey

Co-authored by Zihang Zhou · 19 authors

Zirui Tang, Weizheng Wang, Zihang Zhou, Yang Jiao, Bangrui Xu, Boyu Niu, Dayou Zhou, Xuanhe Zhou, Guoliang Li, Yeye He, Wei Zhou, Yitong Song, Cheng Tan, Xue Yang, Chunwei Liu, Bin Wang, Conghui He, Xiaoyang Wang, Fan Wu

A survey of LLM-powered data analysis across structured, semi-structured, unstructured, and heterogeneous data. My contributions focus on video and 3D-model analysis.