Related papers: Polycraft World AI Lab (PAL): An Extensible Platfo…

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for…

Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making for open-ended tasks.…

The increasing integration of artificial intelligence (AI) in everyday life brings with it new challenges and questions for regarding how humans interact with autonomous agents. Multi-agent experiments, where humans and AI act together, can…

Agentic AI is transforming security by automating many tasks being performed manually. While initial agentic approaches employed a monolithic architecture, the Model-Context-Protocol has now enabled a remote-procedure call (RPC) paradigm to…

Deep Active Learning (DAL) reduces annotation costs by selecting the most informative unlabeled samples during training. As real-world applications become more complex, challenges stemming from distribution shifts (e.g., open-set…

Cooperative multi-agent reinforcement learning (MARL) has made substantial strides in addressing the distributed decision-making challenges. However, as multi-agent systems grow in complexity, gaining a comprehensive understanding of their…

The AIED community envisions AI evolving "from tools to teammates," yet most research still examines AI agents primarily through one-on-one human-AI interactions. We provide an alternative perspective: a rapidly growing ecosystem of AI…

In this paper, we propose Unreal Multi-Agent Playground (Unreal-MAP), an MARL general platform based on the Unreal-Engine (UE). Unreal-MAP allows users to freely create multi-agent tasks using the vast visual and physical resources…

With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC…

Meta-World is widely used for evaluating multi-task and meta-reinforcement learning agents, which are challenged to master diverse skills simultaneously. Since its introduction however, there have been numerous undocumented changes which…

Annotating bounding boxes is costly and limits the scalability of object detection. This challenge is compounded by the need to preserve high accuracy while minimizing manual effort in real-world applications. Prior active learning methods…

Recent advances in reinforcement learning (RL) heavily rely on a variety of well-designed benchmarks, which provide environmental platforms and consistent criteria to evaluate existing and novel algorithms. Specifically, in multi-agent RL…

This work introduces a novel, modular, layered web based platform for managing machine learning experiments on grid-based High Performance Computing infrastructures. The coupling of the communication services offered by the grid, with an…

Imagine a world where AI can handle your work while you sleep - organizing your research materials, drafting a report, or creating a presentation you need for tomorrow. However, while current digital agents can perform simple tasks, they…

Multi-agent reinforcement learning (MARL) is a powerful paradigm for solving cooperative and competitive decision-making problems. While many MARL benchmarks have been proposed, few combine continuous state and action spaces with…

The vision of a broadly capable and goal-directed agent, such as an Internet-browsing agent in the digital world and a household humanoid in the physical world, has rapidly advanced, thanks to the generalization capability of foundation…

Although large language model (LLM)-based agents, exemplified by OpenClaw, are increasingly evolving from task-oriented systems into personalized AI assistants for solving complex real-world tasks, their practical deployment also introduces…

Some standardized environments have been designed for partially observable multi-agent cooperation, but we find most current environments are synchronous, whereas real-world agents often have their own action spaces leading to asynchrony.…

Existing evaluation suites for multi-agent reinforcement learning (MARL) do not assess generalization to novel situations as their primary objective (unlike supervised-learning benchmarks). Our contribution, Melting Pot, is a MARL…

The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…