26 citations · 122 across the 24 of their papers we have counts for
27 papers
ParallelPilot: Supporting Coordination and Monitoring in Parallel AI Coding
Tao Long, Weili Shi, Hussein Mozannar +2
As coding assistants become increasingly autonomous, developers run multiple sessions in parallel, shifting the challenge from code generation alone to coordinating and monitoring…
Fara-1.5: Scalable Learning Environments for Computer Use Agents
Ahmed Awadallah, Sahil Gupta, Yash Lara +12
Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies. This requires two key ingredients: environment…
SentinelBench: A Benchmark for Long-Running Monitoring Agents
Matheus Kunzler Maldaner, Adam Fourney, Amanda Swearngin +5
AI agents are increasingly asked to carry out work that spans minutes, hours, or longer. Yet the default model of agent behavior is continuous action: issuing tool calls, refreshin…
AI-Assisted Systematization for Evaluating GenAI Systems
Dhruv Agarwal, Emily Sheng, Chad Atalla +6
Evaluating generative AI (GenAI) systems is challenging because many targets of evaluation are broad, contested concepts, such as "reasoning," "fairness," or "creativity." When the…
Overseeing Agents Without Constant Oversight: Challenges and Opportunities
Madeleine Grunde-McLaughlin, Hussein Mozannar, Maya Murad +3
To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail re…
Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets
Gagan Bansal, Wenyue Hua, Zezhou Huang +21
As LLM agents advance, they are increasingly mediating economic decisions, ranging from product discovery to transactions, on behalf of users. Such applications promise benefits bu…
Magentic-UI: Towards Human-in-the-loop Agentic Systems
Hussein Mozannar, Gagan Bansal, Cheng Tan +17
AI agents powered by large language models are increasingly capable of autonomously completing complex, multi-step tasks using external tools. Yet, they still fall short of human-l…
Optimizing Sequential Multi-Step Tasks with Parallel LLM Agents
Enhao Zhang, Erkang Zhu, Gagan Bansal +3
Large language model (LLM)-based multi-agent systems have demonstrated remarkable promise for tackling complex tasks by breaking them down into subtasks that are iteratively planne…
CodingGenie: A Proactive LLM-Powered Programming Assistant
Sebastian Zhao, Alan Zhu, Hussein Mozannar +3
While developers increasingly adopt tools powered by large language models (LLMs) in day-to-day workflows, these tools still require explicit user invocation. To seamlessly integra…
Navigating Rifts in Human-LLM Grounding: Study and Benchmark
Omar Shaikh, Hussein Mozannar, Gagan Bansal +2
Language models excel at following instructions but often struggle with the collaborative aspects of conversation that humans naturally employ. This limitation in grounding -- the…
Challenges in Human-Agent Communication
Gagan Bansal, Jennifer Wortman Vaughan, Saleema Amershi +5
Remarkable advancements in modern generative foundation models have enabled the development of sophisticated and highly capable autonomous agents that can observe their environment…
Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
Adam Fourney, Gagan Bansal, Hussein Mozannar +17
Modern AI agents, driven by advances in large foundation models, promise to enhance our productivity and transform our lives by augmenting our knowledge and capabilities. To achiev…
Need Help? Designing Proactive AI Assistants for Programming
Valerie Chen, Alan Zhu, Sebastian Zhao +3
While current chat-based AI assistants primarily operate reactively, responding only when prompted by users, there is significant potential for these systems to proactively assist…
The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers
Hussein Mozannar, Valerie Chen, Mohammed Alsobay +7
Evaluation of large language models for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), or more recently using human preferences of LLM res…
Impact of Large Language Model Assistance on Patients Reading Clinical Notes: A Mixed-Methods Study
Niklas Mannhardt, Elizabeth Bondi-Kelly, Barbara Lam +10
Large language models (LLMs) have immense potential to make information more accessible, particularly in medicine, where complex medical jargon can hinder patient comprehension of…
Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
Hussein Mozannar, Jimin J Lee, Dennis Wei +3
People are relying on AI agents to assist them with various tasks. The human must know when to rely on the agent, collaborate with the agent, or ignore its suggestions. In this wor…
In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer
Yuzhou Cao, Hussein Mozannar, Lei Feng +2
Enabling machine learning classifiers to defer their decision to a downstream expert when the expert is more accurate will ensure improved safety and performance. This objective ca…
When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming
Hussein Mozannar, Gagan Bansal, Adam Fourney +1
AI powered code-recommendation systems, such as Copilot and CodeWhisperer, provide code suggestions inside a programmer's environment (e.g., an IDE) with the aim of improving produ…
Closing the Gap in High-Risk Pregnancy Care Using Machine Learning and Human-AI Collaboration
Hussein Mozannar, Yuria Utsumi, Irene Y. Chen +4
A high-risk pregnancy is a pregnancy complicated by factors that can adversely affect the outcomes of the mother or the infant. Health insurers use algorithms to identify members w…
Who Should Predict? Exact Algorithms For Learning to Defer to Humans
Hussein Mozannar, Hunter Lang, Dennis Wei +3
Automated AI classifiers should be able to defer the prediction to a human decision maker to ensure more accurate predictions. In this work, we jointly train a classifier with a re…
Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
Hussein Mozannar, Gagan Bansal, Adam Fourney +1
Code-recommendation systems, such as Copilot and CodeWhisperer, have the potential to improve programmer productivity by suggesting and auto-completing code. However, to fully real…
Sample Efficient Learning of Predictors that Complement Humans
Mohammad-Amin Charusaie, Hussein Mozannar, David Sontag +1
One of the goals of learning algorithms is to complement and reduce the burden on human decision makers. The expert deferral setting wherein an algorithm can either predict on its…
Teaching Humans When To Defer to a Classifier via Exemplars
Hussein Mozannar, Arvind Satyanarayan, David Sontag
Expert decision makers are starting to rely on data-driven automated agents to assist them with various tasks. For this collaboration to perform properly, the human decision maker…
Consistent Estimators for Learning to Defer to an Expert
Hussein Mozannar, David Sontag
Learning algorithms are often used in conjunction with expert decision makers in practical scenarios, however this fact is largely ignored when designing these algorithms. In this…