Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

Foundation Protocol: A Coordination Layer for Agentic Society

Published in arXiv preprint arXiv:2605.23218, 2026

A graph-first coordination layer that unifies agents, humans, tools, resources, institutions, and organizations while supporting collaboration, economic exchange, provenance, and accountability.

Recommended citation: Bang Liu, Yongfeng Gu, Jiayi Zhang, Zhaoyang Yu, Sirui Hong, Maojia Song, Xiaoqiang Wang, Mingyi Deng, Zijie Zhuang, Ronghao Wang, Mingzhe Cao, Yutong Zhu, Xingjian Li, Yifan Wu, Jianhao Ruan, Yiran Peng, Shuangrui Chen, Jinlin Wang, Yizhang Lin, Dongjie Zhang, Dekun Wu, Chen Ma, Lizi Liao, Han Yu, Jian Pei, Heng Ji, Qiang Yang, Yuyu Luo, Chenglin Wu. (2026). "Foundation Protocol: A Coordination Layer for Agentic Society." arXiv:2605.23218.
Download Paper

ReCode: Unify Plan and Action for Universal Granularity Control

Published in arXiv preprint arXiv:2510.23564, 2025

A paradigm that unifies planning and action through recursive code generation, enabling LLM agents to dynamically control their decision granularity.

Recommended citation: Zhaoyang Yu, Jiayi Zhang, Huixue Su, Yufan Zhao, Yifan Wu, Mingyi Deng, Jinyu Xiang, Yizhang Lin, Lingxiao Tang, Yuyu Luo, Bang Liu, Chenglin Wu. (2025). "ReCode: Unify Plan and Action for Universal Granularity Control." arXiv:2510.23564.
Download Paper

Conference Papers

InfoPO: Information-Driven Policy Optimization for User-Centric Agents

Published in International Conference on Machine Learning (ICML), 2026

Frames multi-turn interaction as active uncertainty reduction, using information-gain rewards to credit turns whose feedback measurably shifts the agent’s action distribution. Accepted at ICML 2026.

Recommended citation: Fanqi Kong, Jiayi Zhang, Mingyi Deng, Chenglin Wu, Yuyu Luo, Bang Liu. (2026). "InfoPO: Information-Driven Policy Optimization for User-Centric Agents." International Conference on Machine Learning (ICML).
Download Paper

InteractComp: Evaluating Search Agents With Ambiguous Queries

Published in International Conference on Machine Learning (ICML), 2025

A benchmark for evaluating whether search agents can recognize query ambiguity and actively interact with users to resolve it during the search process. Accepted at ICML 2026.

Recommended citation: Mingyi Deng, Lijun Huang, Yani Fan, Jiayi Zhang, Fashen Ren, Jinyi Bai, Fuzhen Yang, Dayi Miao, Zhaoyang Yu, Yifan Wu, Yanfei Zhang, Fengwei Teng, Yingjia Wan, Song Hu, Yude Li, Xin Jin, Conghao Hu, Haoyu Li, Qirui Fu, Tai Zhong, Xinyu Wang, Xiangru Tang, Nan Tang, Chenglin Wu, Yuyu Luo. (2026). "InteractComp: Evaluating Search Agents With Ambiguous Queries." International Conference on Machine Learning (ICML).
Download Paper