Related papers: OSGym: Scalable OS Infra for Computer Use Agents
Deep research systems represent an emerging class of agentic information retrieval methods that generate comprehensive and well-supported reports to complex queries. However, most existing frameworks rely on dynamic commercial search APIs,…
A/B testing remains the gold standard for evaluating e-commerce UI changes, yet it diverts traffic, takes weeks to reach significance, and risks harming user experience. We introduce SimGym, a scalable system for rapid offline A/B testing…
Over a past few decades, VM's or Virtual machines have sort of gained a lot of momentum, especially for large scale enterprises where the need for resource optimization & power save is humongous, without compromising with performance or…
General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling…
Quantum computing not only holds the potential to solve long-standing problems in quantum physics, but also to offer speed-ups across a broad spectrum of other fields. However, due to the noise and the limited scale of current quantum…
Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer use data and foundation models. In this…
We introduce ComputerRL, a framework for autonomous desktop intelligence that enables agents to operate complex digital workspaces skillfully. ComputerRL features the API-GUI paradigm, which unifies programmatic API calls and direct GUI…
AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulnerability, which is not yet an attack, into a concrete…
Artificial intelligence (AI) has become a powerful tool for economic research, enabling large-scale simulation and policy optimization. However, applying AI effectively requires simulation platforms for scalable training and evaluation-yet…
Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely overlook agents' ability to orchestrate tools for such rigorous workflows. To bridge this gap,…
To reduce the carbon footprint of computing and stabilize electricity grids, there is an increasing focus on approaches that align the power usage of IT infrastructure with the availability of clean energy. Unfortunately, research on…
With the shrinking of technology nodes and the use of parallel processor clusters in hostile and critical environments, such as space, run-time faults caused by radiation are a serious cross-cutting concern, also impacting architectural…
In order to practically implement the door opening task, a policy ought to be robust to a wide distribution of door types and environment settings. Reinforcement Learning (RL) with Domain Randomization (DR) is a promising technique to…
We introduce MedAgentGym, a scalable and interactive training environment designed to enhance coding-based biomedical reasoning capabilities in large language model (LLM) agents. MedAgentGym comprises 72,413 task instances across 129…
Reproducibility in simulation-based computer architecture research requires coordinating artifacts like disk images, kernels, and benchmarks, but existing workflows are inconsistent. We improve gem5, an open-source simulator with over 1600…
Memory has become the primary cost driver in cloud data centers. Yet, a significant portion of memory allocated to VMs in public clouds remains unused. To optimize this resource, "cold" memory can be reclaimed from VMs and stored on slower…
Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory…
Integrity is critical for maintaining system security, as it ensures that only genuine software is loaded onto a machine. Although confidential virtual machines (CVMs) function within isolated environments separate from the host, it is…
Coworking AI agents operating within local file systems are rapidly emerging as a paradigm in human-AI interaction; however, effective personalization remains limited by severe data constraints, as strict privacy barriers and the difficulty…
The development of native computer-use agents (CUA) represents a significant leap in multimodal AI. However, their potential is currently bottlenecked by the constraints of static data scaling. Existing paradigms relying primarily on…