Research
Current Projects
Negotiating Agents: Strategic and Behavioral Evaluation
University of Michigan | Ongoing
- General AI Agents for Negotiation: Developing methods to fine-tune LLMs for negotiation using game theory and multi-agent reinforcement learning.
- An Iterative Meta-Game Analysis: Creating algorithmic and game-theoretic tools to better understand and interpret the behavior of multiagent systems.
Mechanistic Interpretability of Mixture-of-Experts
University of Michigan | Ongoing
Investigating how expert routing and specialization emerge in Mixture-of-Experts architectures.
Publications
Measuring Competition and Cooperation in LLM Bargaining: An Empirical Meta-Game Analysis
Author(s): Gabriel Smithline, Chris Mascioli, Mithun Chakraborty, and Michael Wellman
University of Michigan | 1st place and winner of the AgentX–AgentBeats Competition, hosted by UC Berkeley RDI | NBER CEME 2026 | Early draft presented at ICML 2025 MAS Workshop | [PDF]
We conduct an empirical game-theoretic analysis of large language models (LLMs) negotiating to divide subjectively valued items, as a case study of assessing advanced AI in mixed-motive settings. Bargaining agents built on proprietary LLMs represent meta-strategies, mapping prompts describing the game to negotiation policies. A graduated series of prompting levels steers agents away from blatant negotiation errors. Across a variety of bargaining scenarios, we estimate empirical meta-games over meta-strategies that include LLM agents, three heuristic strategies representing extreme negotiation attitudes, two reinforcement-learning-derived policies, and an agent based on common bargaining heuristics. We evaluate agents at meta-game equilibria in terms of individual effectiveness, social welfare, and fairness, using bootstrap methods to quantify uncertainty. Our analysis reveals a positive association between individual effectiveness and social metrics across models, with performance varying systematically across providers, architectures, and prompting levels. Behavioral analyses further illuminate why certain models excel or fail in specific bargaining regimes and uncover distinct qualitative patterns across OpenAI, Anthropic, and Google models.
Matching at the Midpoint: A Strategic Agent Based Analysis
Author(s): Gabriel Smithline, Anri Gu, and Michael Wellman
University of Michigan | 2025 | ACM International Conference on AI in Finance 2025 (ICAIF) | Selected for Oral Presentation (top 15%) | [PDF]
We study midpoint matching through Nasdaq's Midpoint Extended-Life Order (M-ELO) mechanism, which offers non-displayed midpoint execution subject to a mandatory holding period to balance liquidity and adverse-selection concerns. We conduct an empirical game-theoretic analysis using an agent-based simulation in PyMarketSim that models both M-ELO and a traditional lit order book, simulating traders' venue choices across a range of holding periods and enumerating pure and mixed Nash equilibria for each setting. We analyze welfare outcomes, strategic stability via deviation graphs, and basins of attraction across these equilibria. Our findings reveal that shorter holding periods can insufficiently deter higher frequency small lot trading, while excessively long delays erode the midpoint premium for large traders. This highlights the fundamental trade-off in designing holding periods that effectively screen predatory trading without undermining value for intended users.
Fast and the Furious: Hot Starts in Pursuit-Evasion Games
Author(s): Gabriel Smithline and Scott Nivison
AFRL Research Project | 2024 | Accepted to ARMS (Autonomous Robots and Multirobot Systems) Workshop at AAMAS 2025 and selected for oral presentation | [PDF]
Effectively positioning pursuers in pursuit-evasion games without prior knowledge of evader locations remains a significant challenge. A novel approach that combines game-theoretic control theory with Graph Neural Networks is introduced in this work. By conceptualizing pursuer configurations as strategic arrangements and representing them as graphs, a Graph Characteristic Space is constructed via multi-objective optimization to identify Pareto-optimal configurations. A Graph Convolutional Network (GCN) is trained on these Pareto-optimal graphs to generate strategically effective initial configurations, termed "hot starts". Empirical evaluations demonstrate that the GCN-generated hot starts provide a significant advantage over random configurations. In scenarios considering multiple pursuers and evaders, this method hastens the decline in evader survival rates, reduces pursuer travel distances, and enhances containment, showcasing clear strategic benefits.
Creating a Cooperative AI Policymaking Platform through Open Source Collaboration
Preprint arXiv:2412.06936
Advances in artificial intelligence (AI) present significant risks and opportunities, requiring improved governance to mitigate societal harms and promote equitable benefits. Current incentive structures and regulatory delays may hinder responsible AI development and deployment, particularly in light of the transformative potential of large language models (LLMs). To address these challenges, we propose developing the following three contributions: (1) a large multimodal text and economic-timeseries foundation model that integrates economic and natural language policy data for enhanced forecasting and decision-making, (2) algorithmic mechanisms for eliciting diverse and representative perspectives, enabling the creation of data-driven public policy recommendations, and (3) an AI-driven web platform for supporting transparent, inclusive, and data-driven policymaking.
Quantal Response-Based Defense in One vs. Many Stackelberg Security Games
Tufts University | 2023-2024 | [PDF]
During the 2023-2024 academic year, I researched Stackelberg Security Games and Deception. My work focused on finding reductions from Stackelberg Security Games to social planner problems in macroeconomic models.
Understanding Eviction Rates Induced by COVID: A Statistical, Mechanism Design, and Game Theoretic Perspective
Lafayette College | 2021
During the 2021 academic year, I researched the impacts of COVID-19 on the rental market in Pennsylvania and Easton. I approached this through statistics, econometrics, mechanism design, and game theory. I worked with the city of Easton to help implement these Mechanism Design solutions.