Related papers: Collaborative Causal Sensemaking: Closing the Comp…
LLMs are increasingly presented as collaborators in programming, design, writing, and analysis. Yet the practical experience of working with them often falls short of this promise. In many settings, users must diagnose misunderstandings,…
What do we want from machine intelligence? We envision machines that are not just tools for thought, but partners in thought: reasonable, insightful, knowledgeable, reliable, and trustworthy systems that think with us. Current artificial…
A Collaborative Artificial Intelligence System (CAIS) is a cyber-physical system that learns actions in collaboration with humans in a shared environment to achieve a common goal. In particular, a CAIS is equipped with an AI model to…
AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI's inferences. A successful partnership requires…
Collaborative tasks often begin with partial task knowledge and incomplete initial plans from each partner. To complete these tasks, agents need to engage in situated communication with their partners and coordinate their partial plans…
A key challenge for the safety of advanced AI systems is the possibility that multiple simpler agents might inadvertently form a collective agent with capabilities and goals distinct from those of any individual. More generally, determining…
Medical decision-making often involves integrating knowledge from multiple clinical specialties, typically achieved through multidisciplinary teams. Inspired by this collaborative process, recent work has leveraged large language models…
My research aims to design systems for complex sensemaking by remotely located non-expert collaborators (crowds), to solve computationally hard problems like crimes.
Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing…
This study explores integrating large language models (LLMs) with situational awareness-based planning (SAP) to enhance the decision-making capabilities of AI agents in dynamic and uncertain environments. We employ a multi-agent reasoning…
Artificial intelligence (AI) systems are deployed as collaborators in human decision-making. Yet, evaluation practices focus primarily on model accuracy rather than whether human-AI teams are prepared to collaborate safely and effectively.…
This study investigates whether large language models (LLMs) can function as intelligent collaborators to bridge expertise gaps in cybersecurity decision-making. We examine two representative tasks-phishing email detection and intrusion…
We develop a network of Bayesian agents that collectively model the mental states of teammates from the observed communication. Using a generative computational approach to cognition, we make two contributions. First, we show that our agent…
Analogical reasoning -- the capacity to identify and map structural relationships between different domains -- is fundamental to human cognition and learning. Recent studies have shown that large language models (LLMs) can sometimes match…
Artificial General Intelligence falls short when communicating role specific nuances to other systems. This is more pronounced when building autonomous LLM agents capable and designed to communicate with each other for real world problem…
As AI becomes an integral part of our lives, the development of explainable AI, embodied in the decision-making process of an AI or robotic agent, becomes imperative. For a robotic teammate, the ability to generate explanations to justify…
This study explores the potential of Human-AI Collaboration (HAIC) use cases as a tool for prospective sensemaking. Based on 14 interviews with executives of an automotive company, we identify and categorize HAIC use cases that can help…
Human decision-making often involves constrained optimization. As LLM agents are deployed to assist with real-world tasks like travel planning, shopping, and scheduling, they must mirror this capability. We introduce COMPASS, a benchmark…
Conventional automated decision-support systems often prioritize predictive accuracy, overlooking the complexities of real-world settings where stakeholders' preferences may diverge or conflict. This can lead to outcomes that disadvantage…
Autonomous agents utilizing Large Language Models (LLMs) have demonstrated remarkable capabilities in isolated medical tasks like diagnosis and image analysis, but struggle with integrated clinical workflows that connect diagnostic…