Related papers: Current Agents Fail to Leverage World Model as Too…
Agent-based social simulation provides a valuable methodology for predicting social information diffusion, yet existing approaches face two primary limitations. Traditional agent models often rely on rigid behavioral rules and lack semantic…
Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the…
Deciding whether an agent possesses a model of its surrounding world is a fundamental step toward understanding its capabilities and limitations. In [10], it was shown that, within a particular framework, every almost optimal and general…
It is crucial to ask how agents can achieve goals by generating action plans using only partial models of the world acquired through habituated sensory-motor experiences. Although many existing robotics studies use a forward model…
Simulations, and more recently LLM agent simulations, have been adopted as useful tools for policymakers to explore interventions, rehearse potential scenarios, and forecast outcomes. While LLM simulations have enormous potential, two…
Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks…
Giving autonomous agents the ability to forecast their own outcomes and uncertainty will allow them to communicate their competencies and be used more safely. We accomplish this by using a learned world model of the agent system to forecast…
As frontier language models are increasingly deployed as autonomous agents pursuing complex, long-term objectives, there is increased risk of scheming: agents covertly pursuing misaligned goals. Prior work has focused on showing agents are…
In planning processes of computational decision-making agents, generative or predictive models are often used as "generators" to propose "targets" representing sets of expected or desirable states. Unfortunately, learned models inevitably…
While reinforcement learning from scratch has shown impressive results in solving sequential decision-making tasks with efficient simulators, real-world applications with expensive interactions require more sample-efficient agents.…
Realistic fine-grained multi-agent simulation of real-world complex systems is crucial for many downstream tasks such as reinforcement learning. Recent work has used generative models (GANs in particular) for providing high-fidelity…
Dynamic game theory is an increasingly popular tool for modeling multi-agent, e.g. human-robot, interactions. Game-theoretic models presume that each agent wishes to minimize a private cost function that depends on others' actions. These…
User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and proactively engages in negotiation by challenging or bargaining. However, current methods…
Constructing general knowledge by learning task-independent models of the world can help agents solve challenging problems. However, both constructing and evaluating such models remains an open challenge. The most common approaches to…
RLHF-aligned LMs have shown unprecedented ability on both benchmarks and long-form text generation, yet they struggle with one foundational task: next-token prediction. As RLHF models become agent models aimed at interacting with humans,…
The landscape of video generation is shifting, from a focus on generating visually appealing clips to building virtual environments that support interaction and maintain physical plausibility. These developments point toward the emergence…
Current Large Language Models (LLMs) exhibit a critical modal disconnect: they possess vast semantic knowledge but lack the procedural grounding to respect the immutable laws of the physical world. Consequently, while these agents…
This paper describes our research on AI agents embodied in visual, virtual or physical forms, enabling them to interact with both users and their environments. These agents, which include virtual avatars, wearable devices, and robots, are…
Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy…
Recent advances in large language models (LLMs) have spurred growing interest in using LLM-integrated agents for social simulation, often under the implicit assumption that realistic population dynamics will emerge once role-specified…