I am a research scientist at ByteDance Research working on LLMs with focus on alignment, agency, and multi-LLM interactions. In addition to this work I also focus on responsible AI and strategic agents.

Papers

Please see my Google Scholar profile for a full list of publications.

[1] ACC-Collab: An Actor Critic Approach to Multi-Agent LLM Collaboration Andrew Estornell $^\dagger$, Jean-François Ton $^\dagger$, Yuanshun Yao, Yang Liu. International Conference on International Conference on Learning Representations (ICLR) 2025. [paper], [pdf]

[2] Multi-LLM Debate: Framework, Principals, and Interventions Andrew Estornell, Yang Liu. Advances in Neural Information Processing Systems (NeurIPS) 2024. [paper]

[3] User-Creator Feature Polarization in Recommender Systems with Dual Influence Tao Lin, Kun Jin, Andrew Estornell, Xiaoying Zhang, Yiling Chen, Yang Liu. Advances in Neural Information Processing Systems (NeurIPS) 2024. [paper]

[4] Measuring and Reducing LLM Hallucination without Gold-Standard Answers Jiaheng Wei, Yuanshun Yao, Jean-Francois Ton, Hongyi Guo, Andrew Estornell, Yang Liu. ArXiv preprint 2024. [paper]

[5] Incentivizing Recourse through Auditing in Strategic Classification. Andrew Estornell, Sanmay Das, Yang Liu, Yatong Chen, Yevgeniy Vorobeychik. [TO APPEAR] International Joint Conference on Artificial Intellegence (IJCAI) 2023.

[6] Unfairness Despite Awareness: Group-Fair Classification with Strategic Agents. Andrew Estornell, Sanmay Das, Yang Liu, Yevgeniy Vorobeychik. [TO APPEAR] Coonference on Fairness Accountability and Transparency (FAccT) 2023. Also appeared in Learning with Strategic Agents (LSA) 2022 (awarded best paper). [link] [pdf]

[7] Popularizing Fairness: Group Fairness and Individual Welfare. Andrew Estornell, Sanmay Das, Brendan Juba, Yevgeniy Vorobeychik. Conference on Artificial Intelligence (AAAI) 2023. [link] [pdf]

[8] Location Spoofing Attacks on Autonomous Fleets. Jinghan Yang, Andrew Estornell, Yevgeniy Vorobeychik. Conference on Vehicle Security and Privacy (VehicleSec) 2023. [paper]

[9] Predicting Customer Goals in Financial Institution Services: A Data-Driven LSTM Approach. Andrew Estornell, Stylianos Loukas Vasileiou, William Yeoh, Daniel Borrajo. International Conference on Automated Planning and Scheduling (ICAPS) Workshop on Planning for Financial Services (FinPlan) 2023. [paper]

[10] Manipulating Elections by Changing Voter Perceptions. Junlin Wu, Andrew Estornell, Lecheng Kong, Yevgeniy Vorobeychik. International Joint Conference on Artificial Intelligence (IJCAI) 2022. [link] [pdf]

[11] Incentivizing Truthfulness Through Audits in Strategic Classification. Andrew Estornell, Sanmay Das, Yevgeniy Vorobeychik. Conference on Artificial Intelligence (AAAI) 2021. [link] [pdf]

[12] Election Control by Manipulating Issue Significance. Andrew Estornell, Sanmay Das, Edith Elkind, Yevgeniy Vorobeychik. Conference on Uncertainty in Artificial Intelligence (UAI) 2020. [link] [pdf]

[13] Deception Through Half-Truths. Andrew Estornell, Sanmay Das, Yevgeniy Vorobeychik. Conference on Artificial Intelligence (AAAI) 2020. [link] [pdf]

[14] PBW Deformations of Quadratic Monomial Algebras. Andrew Estornell, Zachary Cline, Chelsea Walton, Matthew Wynne. Communications in Algebra 2019. [link] [pdf]