Related papers: NovPhy: A Testbed for Physical Reasoning in Open-w…

Artificial Intelligence (AI) has become essential in modern healthcare, with large language models (LLMs) offering promising advances in clinical decision-making. Traditional model-based approaches, including those leveraging in-context…

Artificial intelligence systems for scientific discovery have demonstrated remarkable potential, yet existing approaches remain largely proprietary and operate in batch-processing modes requiring hours per research cycle, precluding…

Generative AI brings novel and impressive abilities to help people in everyday tasks. There are many AI workflows that solve real and complex problems by chaining AI outputs together with human interaction. Although there is an undeniable…

Virtual environments are essential to AI agent research. Existing environments for LLM agent research typically focus on either physical task solving or social simulation, with the former oversimplifying agent individuality and social…

Resolving team conflicts requires not only task-specific competence, but also social intelligence to find common ground and build consensus. As AI agents increasingly collaborate on complex work, they must develop coordination capabilities…

Open-world novelty occurs when the rules of an environment can change abruptly, such as when a game player encounters "house rules". To address open-world novelty, game playing agents must be able to detect when novelty is injected, and to…

AI systems make decisions in physical environments through primitive actions or affordances that are accessed via API calls. While deploying AI agents in the real world involves numerous high-level actions, existing embodied simulators…

Adaptive experiments automatically optimize their design throughout the data collection process, which can bring substantial benefits compared to conventional experimental settings. Potential applications include, among others: computerized…

We pose an active perception problem where an autonomous agent actively interacts with a second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the other agent, the objective is to collect further…

We introduce BusyBoard, a toy-inspired robot learning environment that leverages a diverse set of articulated objects and inter-object functional relations to provide rich visual feedback for robot interactions. Based on this environment,…

This paper presents the Articulated Animal AI Environment for Animal Cognition, an enhanced version of the previous AnimalAI Environment. Key improvements include the addition of agent limbs, enabling more complex behaviors and interactions…

Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and…

Human-like Agents with diverse and dynamic personalities could serve as an essential design probe in the process of user-centered design, thereby enabling designers to enhance the user experience of interactive applications. In this…

Physical AI systems need to perceive, understand, and perform complex actions in the physical world. In this paper, we present the Cosmos-Reason1 models that can understand the physical world and generate appropriate embodied decisions…

In this work a general framework is proposed to support the development of software systems that are able to adapt their behaviour according to the operating environment changes. The proposed approach, named REPTILE, works in a complete…

According to canonical negotiation theory, people's success in a negotiation depends on how well they balance competing demands--empathizing and asserting, demonstrating concern for other and concern for self, being soft on the people and…

Artificial agents' adaptability to novelty and alignment with intended behavior is crucial for their effective deployment. Reinforcement learning (RL) leverages novelty as a means of exploration, yet agents often struggle to handle novel…

In many reinforcement learning tasks, the goal is to learn a policy to manipulate an agent, whose design is fixed, to maximize some notion of cumulative reward. The design of the agent's physical structure is rarely optimized for the task…

What if artificial agents could not just communicate, but also evolve, adapt, and reshape their worlds in ways we cannot fully predict? With llm now powering multi-agent systems and social simulations, we are witnessing new possibilities…

Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and productivity. However, existing benchmarks…