Related papers: Cradle: Empowering Foundation Agents Towards Gener…
AI agents increasingly perform agentic exploration: pursuing multiple solution paths in parallel and committing only the successful one. Because each exploration path may modify files and spawn processes, agents require isolated…
We aim to develop a goal specification method that is semantically clear, spatially sensitive, domain-agnostic, and intuitive for human users to guide agent interactions in 3D environments. Specifically, we propose a novel cross-view goal…
GUI agents drive applications through their visual interfaces instead of programmatic APIs, interacting with arbitrary software via taps, swipes, and keystrokes, reaching a long tail of applications that CLI-based agents cannot. Yet…
Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in…
Recent works have been exploring the scaling laws in the field of Embodied AI. Given the prohibitive costs of collecting real-world data, we believe the Simulation-to-Real (Sim2Real) paradigm is a crucial step for scaling the learning of…
Autonomous agents operating on the graphical user interfaces (GUIs) of various applications hold immense practical value. Unlike the large language model (LLM)-based methods which rely on structured texts and customized backends, the…
Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code…
Modern manufacturing under High-Mix-Low-Volume requirements increasingly relies on flexible and adaptive matrix production systems, which depend on interconnected heterogeneous devices and rapid task reconfiguration. To address these needs,…
Recent advances in foundation models, particularly Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), have facilitated the development of intelligent agents capable of performing complex tasks. By leveraging the…
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…
There is an increasing interest in executing complex analyses over large graphs, many of which require processing a large number of multi-hop neighborhoods or subgraphs. Examples include ego network analysis, motif counting, personalized…
Agentic exploration, letting LLM-powered agents branch, backtrack, and search across many execution paths, demands systems support well beyond today's pass-at-k resets. Our benchmark of six snapshot/restore mechanisms shows that generic…
The rapid development of GUI foundation models and mobile GUI agents has spurred numerous evaluation benchmarks, yet most rely on simulated environments or open-source applications, leaving real-world closed-source applications largely…
In today's rapidly evolving military landscape, advancing artificial intelligence (AI) in support of wargaming becomes essential. Despite reinforcement learning (RL) showing promise for developing intelligent agents, conventional RL faces…
Cooperative multi-agent reinforcement learning (MARL) aims to develop agents that can collaborate effectively. However, most cooperative MARL methods overfit training agents, making learned policies not generalize well to unseen…
Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents. A representative scenario is in software development, where agents can collaborate in a team like humans,…
To observe how individual behavior shapes a larger community's actions, agent-based modeling and simulation (ABMS) has been widely adopted by researchers in social sciences, economics, and epidemiology. While simulations can be run on…
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.…
Graph-based representations and message-passing modular policies constitute prominent approaches to tackling composable control problems in reinforcement learning (RL). However, as shown by recent graph deep learning literature, such local…
Trading off performance guarantees in favor of scalability, the Multi-Agent Path Finding (MAPF) community has recently started to embrace Multi-Agent Reinforcement Learning (MARL), where agents learn to collaboratively generate individual,…