Full list on Google Scholar
Introduces Task-Environment-Agents (TEA), a structural representation that couples an Agent Interaction Graph with a Task Activity Graph and the shared environment. It makes evolving collaboration explicit without prescribing agent reasoning, behavior, or communication order, and Infuse uses TEA records to recover, assess, and improve collaboration policies.
Represents emergent collaboration through coupled cooperation-obligation graphs that formalize work soundness and assignment stability. Their joint satisfaction quantifies state quality and yields a conditional performance bound.
Formalizes cooperation from two connected sides: what cooperative tasks require and how LLM agents reason, communicate, use tools, and act across cognitive and primitive layers. Aligning both makes cooperation observable, while the COOP2-Repair case study highlights how the formulation can support targeted replanning.
Coordinates embodied agents through two phases: agents negotiate and commit to roles, then independently execute symbolic plans grounded in a shared world model. Working above raw trajectories makes collaboration more reusable and interpretable while allowing the world model to improve across episodes.
Designs weighted blocks, force, congestion, collisions, and timing so task-induced dependencies and collective capability become explicit. Some goals are individually infeasible, allowing collaboration to be studied as a property of the task rather than only of the policy.
First Place (tie), Decentralized and Multi-Agents Track · Berkeley RDI LLM Agents MOOC Hackathon
Introduces DAMCS, whose adaptive hierarchical knowledge graph organizes multimodal experience into shared and local memory. Decentralized agents can reason from past interactions while sharing relevant knowledge rather than entire histories during long-horizon planning under dependency constraints.
Uses an LLM-based digital twin to simulate heterogeneous human feedback for adaptive HVAC control. Aggregated occupant preferences enter the reward objective, making collective preference part of what the controller learns to optimize.
Machine Learning for Healthcare
Before focusing on multi-agent systems, I worked closely with clinicians on decision support and scarce-resource allocation across international, national, and local datasets. These projects moved from validating risk scores, to aligning predictions with clinical decision horizons, to estimating treatment effects when a potentially beneficial intervention cannot be given to every eligible patient.
Developed calibrated predictions at multiple time horizons for critically ill COVID-19 patients, aligning risk estimates with when scarce ECMO allocation decisions must be made.
Used disentangled latent representations to separate prognostic factors from heterogeneous treatment effects, supporting decisions when treatment capacity is limited.
Evaluated mortality prediction and severity-of-illness scores in an international COVID-19 cohort, testing how established tools behave across a diverse clinical population.