Related papers: MineStudio: A Streamlined Package for Minecraft AI…
Agentic systems built on large language models (LLMs) offer promising capabilities for automating complex workflows in healthcare AI. We introduce mAIstro, an open-source, autonomous multi-agentic framework for end-to-end development and…
Long-horizon embodied intelligence requires agents to improve through interaction, not merely to execute plans generated from static goals. A central challenge is therefore to transform past executions into knowledge that can shape future…
Enhancing AI systems with efficient communication skills for effective human assistance necessitates proactive initiatives from the system side to discern specific circumstances and interact aptly. This research focuses on a collective…
Advances in deep generative modeling have made it increasingly plausible to train human-level embodied agents. Yet progress has been limited by the absence of large-scale, real-time, multi-modal, and socially interactive datasets that…
Existing action-conditioned video generation models (video world models) are limited to single-agent perspectives, failing to capture the multi-agent interactions of real-world environments. We introduce Solaris, a multiplayer video world…
AI systems represented by AlphaFold are rapidly expanding the scale of protein structure modelling data, and the MineProt project provides an effective solution for custom curation of these novel high-throughput data. It enables researchers…
Recently, large language models (LLMs) have evolved into interactive agents, proficient in planning, tool use, and task execution across a wide variety of tasks. However, without specific agent tuning, open-source models like LLaMA…
In recent years, AI-based software engineering has progressed from pre-trained models to advanced agentic workflows, with Software Development Agents representing the next major leap. These agents, capable of reasoning, planning, and…
Game agents such as opponents, non-player characters, and teammates are central to player experiences in many modern games. As the landscape of AI techniques used in the games industry evolves to adopt machine learning (ML) more widely, it…
Building open agents has always been the ultimate goal in AI research, and creative agents are the more enticing. Existing LLM agents excel at long-horizon tasks with well-defined goals (e.g., `mine diamonds' in Minecraft). However, they…
We propose a new benchmark for planning tasks based on the Minecraft game. Our benchmark contains 45 tasks overall, but also provides support for creating both propositional and numeric instances of new Minecraft tasks automatically. We…
In the pursuit of artificial general intelligence, our most significant measurement of progress is an agent's ability to achieve goals in a wide range of environments. Existing platforms for constructing such environments are typically…
The balance of game content significantly impacts the gaming experience. Unbalanced game content diminishes engagement or increases frustration because of repetitive failure. Although game designers intend to adjust the difficulty of game…
We investigate the challenge of task planning for multi-task embodied agents in open-world environments. Two main difficulties are identified: 1) executing plans in an open-world environment (e.g., Minecraft) necessitates accurate and…
Progress in multiagent intelligence research is fundamentally limited by the number and quality of environments available for study. In recent years, simulated games have become a dominant research platform within reinforcement learning, in…
The growing prevalence of artificial intelligence (AI) in various applications underscores the need for agents that can successfully navigate and adapt to an ever-changing, open-ended world. A key challenge is ensuring these AI agents are…
With the increasing integration of large lauguage models (LLMs) in education, there is growing interest in using AI agents to support student learning in creative tasks. This study presents an interactive Mentor Agent system named Mentigo,…
Large Language Models (LLMs) have shown great success as high-level planners for zero-shot game-playing agents. However, these agents are primarily evaluated on Minecraft, where long-term planning is relatively straightforward. In contrast,…
Real-world tasks of interest are generally poorly defined by human-readable descriptions and have no pre-defined reward signals unless it is defined by a human designer. Conversely, data-driven algorithms are often designed to solve a…
Minecraft, as an open-world virtual interactive environment, has become a prominent platform for research on agent decision-making and execution. Existing works primarily adopt a single Large Language Model (LLM) agent to complete various…