Autonomous agents have long been a research focus in academic and industry
communities. Previous research often focuses on training agents with limited knowledge …

Large Language Models (LLMs) went from non-existent to ubiquitous in the machine
learning discourse within a few years. Due to the fast pace of the field, it is difficult to identify …

Large language models excel at a wide range of complex tasks. However, enabling general
inference in the real world, eg, for robotics problems, raises the challenge of grounding. We …

We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft
that continuously explores the world, acquires diverse skills, and makes novel discoveries …

Agents capable of carrying out general tasks on a computer can improve efficiency and
productivity by automating repetitive tasks and assisting in complex problem-solving. Ideally …

For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing
the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are …

There is a growing interest in applying pre-trained large language models (LLMs) to
planning problems. However, methods that use LLMs directly as planners are currently …

Constructing AI models that respond to text instructions is challenging, especially for
sequential decision-making tasks. This work introduces an instruction-tuned Video …

Reward specification is a notoriously difficult problem in reinforcement learning, requiring
extensive expert supervision to design robust reward functions. Imitation learning (IL) …

We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of
human cognition, designed to excel in action planning for complex interactive reasoning …