Publications

Preprint

The Helpful Agent Problem: When Emergent Cooperation Among LLM Agents Bypasses Intended Workflows

Moumita Choudhury, Amit Sarker, and Shlomo Zilberstein

arXiv:2610.31985, 2026.

Workshop paper · Preprint

Training Language Models to Cooperate with Inference-Time Controllers

Moumita Choudhury, Vanshaj Khattar, Jing Liu, Toshiaki Koike-Akino, Ankush Chakrabarty, Shlomo Zilberstein, and Ye Wang

Accepted to the Workshop on Towards Test-Time Continual Learning Agents (TTCL) at NeurIPS 2026. Preprint: arXiv:2607.23771.

Workshop paper

The Benefits and Limits of Trust Models in Repeated Multi-Party Negotiation with LLM Agents

Amit Sarker, Moumita Choudhury, Saaduddin Mahmud, and Shlomo Zilberstein

Accepted to the Second Workshop on Large Language Models for Social Reasoning and Simulation (SocialAgent) at NeurIPS 2026.

Workshop paper · Preprint

Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities

Vanshaj Khattar, Md Rafi ur Rashid, Moumita Choudhury, Jing Liu, Toshiaki Koike-Akino, Ming Jin, and Ye Wang

Workshop on Trust and Control in Agentic AI (TrustAgent) at AAAI 2026. Preprint: arXiv:2603.15417.

Authors are listed in the order of the arXiv version.

Workshop paper · Spotlight

Bayesian Inverse Reinforcement Learning Approach for Policy Summarization

Moumita Choudhury, Shuwa Miura, and Shlomo Zilberstein

Advancing Artificial Intelligence through Theory of Mind (ToM4AI), AAAI 2025 workshop.

Conference paper · Extended abstract

Minimizing Negative Side Effects in Cooperative Multi-Agent Systems Using Distributed Coordination

Moumita Choudhury, Sandhya Saisubramanian, Hao Zhang, and Shlomo Zilberstein

The International FLAIRS Conference Proceedings, volume 37, 2024. Also appeared as an extended abstract at the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2024.

Journal article · DCOP

A Particle Swarm Inspired Approach for Continuous Distributed Constraint Optimization Problems

Moumita Choudhury, Amit Sarker, Samin Yaser, Md Maruf Al Alif Khan, William Yeoh, and Md Mosaddek Khan

Engineering Applications of Artificial Intelligence, volume 123, article 106280, 2023.

Conference paper · DCOP

A Local Search Based Approach to Solve Continuous DCOPs

Amit Sarker, Moumita Choudhury, and Md. Mosaddek Khan

Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1127–1135, 2021.

Conference paper · DCOP

A Particle Swarm Based Algorithm for Functional Distributed Constraint Optimization Problems

Moumita Choudhury, Saaduddin Mahmud, and Md. Mosaddek Khan

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, volume 34(05), pages 7111–7118, 2020.

Conference paper · DCOP

AED: An Anytime Evolutionary DCOP Algorithm

Saaduddin Mahmud, Moumita Choudhury, Md. Mosaddek Khan, Long Tran-Thanh, and Nicholas R. Jennings

Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 825–833, 2020.

Conference paper · DCOP

Learning Optimal Temperature Region for Solving Mixed Integer Functional DCOPs

Saaduddin Mahmud, Md. Mosaddek Khan, Moumita Choudhury, Long Tran-Thanh, and Nicholas R. Jennings

Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI-PRICAI), pages 268–275, 2020.

Extended abstract · Workshop paper · DCOP

C-CoCoA: A Continuous Cooperative Constraint Approximation Algorithm to Solve Functional DCOPs

Amit Sarker, Abdullahil Baki Arif, Moumita Choudhury, and Md. Mosaddek Khan

Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), extended abstract, pages 1990–1992, 2020. Also presented at the 11th International Workshop on Optimization and Learning in Multiagent Systems (OptLearnMAS) at AAMAS 2020.