Related papers: See, Think, Act: Teaching Multimodal Agents to Eff…
Agentic AI represents a major shift in how autonomous systems reason, plan, and execute multi-step tasks through the coordination of Large Language Models (LLMs), Vision Language Models (VLMs), tools, and external services. While these…
Recent progress in multimodal large language models (MLLMs) has demonstrated promising performance on medical benchmarks and in preliminary trials as clinical assistants. Yet, our pilot audit of diagnostic cases uncovers a critical failure…
The growing complexity of intelligent transportation systems and their applications in public spaces has increased the demand for expressive and versatile knowledge representation. While various mapping efforts have achieved widespread…
Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions. However, the sparse reward signals offered by the KG during traversal are often…
The complexity of the real world demands robotic systems that can intelligently adapt to unseen situations. We present STEER, a robot learning framework that bridges high-level, commonsense reasoning with precise, flexible low-level…
Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to Tool Overuse, where models…
Matching patients effectively and efficiently for clinical trials is a significant challenge due to the complexity and variability of patient profiles and trial criteria. This paper introduces \textbf{Multi-Agent for Knowledge Augmentation…
Most commodity software lacks accessible Application Programming Interfaces (APIs), requiring autonomous agents to interact solely through pixel-based Graphical User Interfaces (GUIs). In this API-free setting, large language model…
Model-based reinforcement learning (MBRL) techniques have recently yielded promising results for real-world autonomous racing using high-dimensional observations. MBRL agents, such as Dreamer, solve long-horizon tasks by building a world…
The current paradigm of test-time scaling relies on generating long reasoning traces ("thinking" more) before producing a response. In agent problems that require interaction, this can be done by generating thinking traces before acting in…
Augmented Reality (AR) offers powerful visualization capabilities for industrial robot training, yet current interfaces remain predominantly static, failing to account for learners' diverse cognitive profiles. In this paper, we present an…
Humans continue to outperform modern AI systems in their ability to flexibly parse and understand complex visual scenes. Here, we present a novel module for visual reasoning, the Guided Attention Model for (visual) Reasoning (GAMR), which…
Autonomous vehicles (AVs) are poised to redefine transportation by enhancing road safety, minimizing human error, and optimizing traffic efficiency. The success of AVs depends on their ability to interpret complex, dynamic environments…
Modeling how human moves in the space is useful for policy-making in transportation, public safety, and public health. Human movements can be viewed as a dynamic process that human transits between states (\eg, locations) over time. In the…
The paper describes a flexible and modular platform to create multimodal interactive agents. The platform operates through an event-bus on which signals and interpretations are posted in a sequence in time. Different sensors and…
In recent years, simulations of pedestrians using the multi-agent reinforcement learning (MARL) have been studied. This study considered the roads on a grid-world environment, and implemented pedestrians as MARL agents using an echo-state…
Scalable multi-agent driving simulation requires behavior models that are both realistic and computationally efficient. We address this by optimizing the behavior model that controls individual traffic participants. To improve efficiency,…
We propose a formalism to model and reason about reconfigurable multi-agent systems. In our formalism, agents interact and communicate in different modes so that they can pursue joint tasks; agents may dynamically synchronize, exchange…
The rapid advancement of large vision language models (LVLMs) and agent systems has heightened interest in mobile GUI agents that can reliably translate natural language into interface operations. Existing single-agent approaches, however,…
Increasing urban concentration raises operational challenges that can benefit from integrated monitoring and decision support. Such complex systems need to leverage the full stack of analytical methods, from state estimation using…