Related papers: OSGym: Scalable OS Infra for Computer Use Agents
Our middleware approach, Context-Oriented Software Middleware (COSM), supports context-dependent software with self-adaptability and dependability in a mobile computing environment. The COSM-middleware is a generic and platform-independent…
Rapid growth of datacenter (DC) scale, urgency of cost control, increasing workload diversity, and huge software investment protection place unprecedented demands on the operating system (OS) efficiency, scalability, performance isolation,…
Cloud computing focuses on delivery of reliable, secure, fault-tolerant, sustainable, and scalable infrastructures for hosting Internet-based application services. These applications have different composition, configuration, and deployment…
Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scarce, and existing synthesis methods suffer from significant…
Effective visual representation learning is crucial for reinforcement learning (RL) agents to extract task-relevant information from raw sensory inputs and generalize across diverse environments. However, existing RL benchmarks lack the…
Compiling a quantum circuit for specific quantum hardware is a challenging task. Moreover, current quantum computers have severe hardware limitations. To make the most use of the limited resources, the compilation process should be…
Sampling is a basic operation in many inference-time algorithms of large language models (LLMs). To scale up inference efficiently with a limited compute, it is crucial to find an optimal allocation for sample compute budgets: Which…
Multi-agent systems powered by large language models have emerged as a promising paradigm for solving complex reasoning tasks through collaborative intelligence. However, efficiently deploying these systems on serverless GPU platforms…
Rapid progress in the development of information technology has led to a significant increase in the number and complexity of cyber threats. Traditional methods of cybersecurity training based on theoretical knowledge do not provide a…
Intelligent task placement and management of tasks in large-scale fog platforms is challenging due to the highly volatile nature of modern workload applications and sensitive user requirements of low energy consumption and response time.…
This work elaborates on a High performance computing (HPC) architecture based on Simple Linux Utility for Resource Management (SLURM) [1] for deploying heterogeneous Large Language Models (LLMs) into a scalable inference engine. Dynamic…
We introduce AgentSynth, a scalable and cost-efficient pipeline for automatically synthesizing high-quality tasks and trajectory datasets for generalist computer-use agents. Leveraging information asymmetry, AgentSynth constructs subtasks…
Serving Large Language Models (LLMs) can benefit immensely from parallelizing both the model and input requests across multiple devices, but incoming workloads exhibit substantial spatial and temporal heterogeneity. Spatially, workloads…
Large language model (LLM)-based computer-use agents represent a convergence of AI and OS capabilities, enabling natural language to control system- and application-level functions. However, due to LLMs' inherent uncertainty issues,…
Reliable Docker-based environment construction is a dominant bottleneck for scaling execution-grounded training and evaluation of software engineering agents. We introduce DockSmith, a specialized agentic Docker builder designed to address…
Neural networks (NNs) can achieved high performance in various fields such as computer vision, and natural language processing. However, deploying NNs in resource-constrained safety-critical systems has challenges due to uncertainty in the…
This paper presents OpenGridGym, an open-source Python-based package that allows for seamless integration of distribution market simulation with state-of-the-art artificial intelligence (AI) decision-making algorithms. We present the…
Computer-use agents hold the promise of assisting in a wide range of digital economic activities. However, current research has largely focused on short-horizon tasks over a limited set of software with limited economic value, such as basic…
Digital agents require diverse, large-scale UI trajectories to generalize across real-world tasks, yet collecting such data is prohibitively expensive in both human annotation, infra and engineering perspectives. To this end, we introduce…
The ever-increasing complexity of HW/SW systems presents a persistent challenge, particularly in safety-critical domains like automotive, where extensive testing is imperative. However, the availability of hardware often lags behind,…