Publications

2026

1. Preprint

   

   RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments

   Sibo Zhu^*, Shicheng Fan^*, Xinyue Wang^*, Wenyi Wu, Kun Zhou, and Biwei Huang

   Under review at ICLR 2027; Hugging Face Daily Papers #6 (Sep 15, 2026); Headline feature in Synced (机器之心), an AI news outlet , 2026

   arXiv Bib PDF Code Website

   @misc{zhu2026rsiagent,
     title = {{RSIAgent}: Autonomous Exploration for Recursive Self-improvement in New Environments},
     author = {Zhu, Sibo and Fan, Shicheng and Wang, Xinyue and Wu, Wenyi and Zhou, Kun and Huang, Biwei},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
   }

2. Preprint

   

   Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce

   Shicheng Fan, Mingdai Yang, Duohao Wang, Canyu Chen, Yongfeng Zhang, Hua Wei, and 6 more authors

   2026

   arXiv Bib PDF Code Website

   @misc{fan2026acworld,
     title = {Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce},
     author = {Fan, Shicheng and Yang, Mingdai and Wang, Duohao and Chen, Canyu and Zhang, Yongfeng and Wei, Hua and Li, Manling and McAuley, Julian and Zhang, Kun and Yu, Philip S. and Yu, Kejing and Liu, Zhiwei},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
   }

3. COLM 2026

   

   CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

   Hanrong Zhang^*, Shicheng Fan^*, Henry Peng Zou, Yankai Chen, Zhenting Wang, Jiayu Zhou, and 7 more authors

   In Conference on Language Modeling (COLM), 2026

   arXiv Bib PDF Code Website

   @inproceedings{zhang2026coevoskills,
     title = {{CoEvoSkills}: Self-Evolving Agent Skills via Co-Evolutionary Verification},
     author = {Zhang, Hanrong and Fan, Shicheng and Zou, Henry Peng and Chen, Yankai and Wang, Zhenting and Zhou, Jiayu and Li, Chengze and Huang, Wei-Chieh and Yao, Yifei and Zheng, Kening and Liu, Xue and Li, Xiaoxiao and Yu, Philip S.},
     booktitle = {Conference on Language Modeling ({COLM})},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
   }

4. ICML 2026

   

   TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning

   Shicheng Fan, Kun Zhang, and Lu Cheng

   In International Conference on Machine Learning (ICML), 2026

   arXiv Bib PDF Code

   @inproceedings{fan2026trace,
     title = {{TRACE}: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning},
     author = {Fan, Shicheng and Zhang, Kun and Cheng, Lu},
     booktitle = {International Conference on Machine Learning ({ICML})},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
   }

5. NeurIPS 2026

   

   MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series

   Shicheng Fan, Nour Elhendawy, Jianle Sun, Ke Fang, Kun Zhang, Yihang Wang, and 1 more author

   In Conference on Neural Information Processing Systems (NeurIPS), 2026

   arXiv Bib PDF Code

   @inproceedings{fan2026mosaic,
     title = {{MOSAIC}: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series},
     author = {Fan, Shicheng and Elhendawy, Nour and Sun, Jianle and Fang, Ke and Zhang, Kun and Wang, Yihang and Cheng, Lu},
     booktitle = {Conference on Neural Information Processing Systems ({NeurIPS})},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
   }

6. Preprint

   

   Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering

   Shicheng Fan^*, Haochang Hao^*, Dehai Min^*, Weihao Liu, Hanrong Zhang, Lingwei Wei, and 7 more authors

   Under review at ICLR 2027 , 2026

   arXiv Bib PDF Code

   @misc{fan2026corver,
     title = {Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering},
     author = {Fan, Shicheng and Hao, Haochang and Min, Dehai and Liu, Weihao and Zhang, Hanrong and Wei, Lingwei and Zou, Henry Peng and Guo, Chengquan and Yang, Jie and Bao, Honghui and Liu, Zhiwei and Cheng, Lu and Yu, Philip S.},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
   }

7. Preprint

   

   Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents

   Mingdai Yang, Shicheng Fan, Kejing Yu, Duohao Wang, Li Sun, Hao Peng, and 2 more authors

   2026

   arXiv Bib PDF

   @misc{yang2026honesty,
     title = {Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for {LLM} Marketplace Agents},
     author = {Yang, Mingdai and Fan, Shicheng and Yu, Kejing and Wang, Duohao and Sun, Li and Peng, Hao and Yu, Philip S. and Liu, Zhiwei},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.AI},
   }

8. Survey

   

   Scaling LLM Agent Learning with Data Synthesis: A Comprehensive Survey

   Hanrong Zhang, Yankai Chen, Shicheng Fan, Dehai Min, Shaowen Chen, Huanhuan Ma, and 25 more authors

   2026

   Bib PDF

   @misc{zhang2026scaling,
     title = {Scaling {LLM} Agent Learning with Data Synthesis: A Comprehensive Survey},
     author = {Zhang, Hanrong and Chen, Yankai and Fan, Shicheng and Min, Dehai and Chen, Shaowen and Ma, Huanhuan and Wu, Zhaofen and Yang, Jie and He, Bowei and Kang, Jikun and Zheng, Kening and Chen, Xi and Miao, Chunyu and Lin, Fulin and Huang, Wei-Chieh and Zhou, Jiayu and Wu, Haolun and Fang, Liancheng and Kang, Hong and He, Langzhou and Zou, Henry Peng and Li, Chengze and Wu, Jialong and Hong, Haiwen and Chen, Zhaorun and Luo, Hanjun and Kong, Linghe and Wang, Hongwei and Song, Dawn and Yu, Philip S. and Liu, Xue},
     year = {2026},
   }