Research

Multi-agent security · cooperative AI · evaluation of agentic systems

2026

OpenSanctions Pairs: Large-Scale Entity Matching with LLMs Chandler Smith, M. Sesodia, F. Lindenberg, C. Schroeder de Witt arXiv preprint, 2026 [arXiv]
Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts A. K. Saeri, J. Graham, M. Noetel, P. Slattery, et al. (incl. Chandler Smith) arXiv preprint, 2026 [arXiv]

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia Chandler Smith, M. Abdulhai, M. Díaz, M. Tesic, R. Trivedi, S. Vezhnevets, L. Hammond, J. Clifton, M. Chang, E. Duéñez-Guzmán, J. Agapiou, J. Matyas, D. Karmon, et al. NeurIPS 2025, Datasets & Benchmarks [arXiv] [OpenReview]
MALT: Improving Reasoning with Multi-Agent LLM Training S. R. Motwani, Chandler Smith, R. J. Das, R. Rafailov, I. Laptev, P. H. S. Torr, F. Pizzati, R. Clark, C. Schroeder de Witt COLM 2025 [arXiv]
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents C. Schroeder de Witt, K. Krawiecka, I. Krawczuk, B. Hagag, W. L. Anderson, P. Belcak, et al. (incl. Chandler Smith) arXiv preprint, 2025 [arXiv] [scholar]
Multi-Agent Risks from Advanced AI L. Hammond, A. Chan, J. Clifton, J. Hoelscher-Obermaier, A. Khan, E. McLean, Chandler Smith, et al. Cooperative AI Foundation, Technical Report #1, 2025 [arXiv]

BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices A. Reuel, A. Hardy, Chandler Smith, M. Lamparth, M. Hardy, M. J. Kochenderfer NeurIPS 2024, Datasets & Benchmarks (Spotlight) [OpenReview] [website]
Escalation Risks from Language Models in Military and Diplomatic Decision-Making J.-P. Rivera, G. Mukobi, A. Reuel, M. Lamparth, Chandler Smith, J. Schneider FAccT 2024 [arXiv] [ACM]
The Concordia Contest: Advancing the Cooperative Intelligence of Language Model Agents Chandler Smith, R. Trivedi, J. Clifton, L. Hammond, A. Khan, S. Vezhnevets, J. Agapiou, E. Duéñez-Guzmán, J. Matyas, D. Karmon, M. Abdulhai, D. Hadfield-Menell, N. Jaques, J. Z. Leibo, O. Slumbers, T. Baarslag, M. Chang NeurIPS 2024, Competition Track [OpenReview] [contest]
Evaluating Language Model Character Traits F. R. Ward, Z. Yang, A. Jackson, R. Brown, Chandler Smith, G. B. Colverd, L. Thomson, R. Douglas, P. Bartak, A. Rowan EMNLP 2024, Findings [arXiv]

Assessing Risks of Using Autonomous Language Models in Military and Diplomatic Planning G. Mukobi, A. Reuel, J.-P. Rivera, Chandler Smith Multi-Agent Security Workshop, NeurIPS 2023