Related papers: OpenJarvis: Personal AI, On Personal Devices
Automating cloud configuration and deployment remains a critical challenge due to evolving infrastructures, heterogeneous hardware, and fluctuating workloads. Existing solutions lack adaptability and require extensive manual tuning, leading…
Specialized clinical AI assistants are rapidly entering medical practice, often framed as safer or more reliable than general-purpose large language models (LLMs). Yet, unlike frontier models, these clinical tools are rarely subjected to…
As artificial intelligence (AI) systems approach and surpass expert human performance across a broad range of tasks, obtaining high-quality human supervision for evaluation and training becomes increasingly challenging. Our focus is on…
As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. However, cloud-assisted memory management exposes sensitive user…
The rise of large language models (LLMs), such as ChatGPT, Gemini, and Grok, has reshaped the AI landscape. As prominent instances of foundational models (FMs), they exhibit remarkable capabilities in generating human-like content, pushing…
Lack of rigorous reproducibility and validation are major hurdles for scientific development across many fields. Materials science in particular encompasses a variety of experimental and theoretical approaches that require careful…
Personalized AI agents are becoming central to modern information retrieval, yet most evaluation methodologies remain static, relying on fixed benchmarks and one-off metrics that fail to reflect how users' needs evolve over time. These…
The transition from optical identification of 2D quantum materials to practical device fabrication requires dynamic reasoning beyond the detection accuracy. While recent domain-specific Multimodal Large Language Models (MLLMs) successfully…
Large Language Models (LLMs) face a crucial challenge from fixed context windows and inadequate memory management, leading to a severe shortage of long-term memory capabilities and limited personalization in the interactive experience with…
The rise of personal assistant agents, e.g., OpenClaw, highlights the growing potential of large language models to support users across everyday life and work. A core challenge in these settings is proactive assistance, since users often…
Automated negotiations in insurance and business-to-business (B2B) commerce encounter substantial challenges. Current systems force a trade-off between convenience and privacy by routing sensitive financial data through centralized servers,…
Large language models (LLMs) such as ChatGPT have evolved into powerful and ubiquitous tools. Fine-tuning on small datasets allows LLMs to acquire specialized skills for specific tasks efficiently. Although LLMs provide great utility in…
Artificial Intelligence (AI) has become a powerful tool for model-free Radio Access Network (RAN) signal processing and optimization. However, designing a single model that generalizes across all radio environments is challenging.…
Despite significant advances in LLM-driven GUI agents, the field remains constrained by the challenge of reconciling high-fidelity realism with verifiable evaluation accuracy. To address this, we introduce NaturalGAIA, a verifiable…
LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on untrusted external content exposes them to indirect prompt injection (IPI), in which…
This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance mechanisms, and early deployment experience. The performance of agent systems built on LLMs…
The recent shift in Generative AI (GenAI) applications from cloud-only environments to end-user devices introduces new challenges in resource management, system efficiency, and user experience. This paper presents ConsumerBench, a…
Rapid detection and mitigation of issues that impact performance and reliability is paramount for large-scale online services. For real-time detection of such issues, datacenter operators use a stream processor and analyze streams of…
Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…
Agentic artificial intelligence (AI) -- multi-agent systems that combine large language models with external tools and autonomous planning -- are rapidly transitioning from research laboratories into high-stakes domains. Our earlier "Basic"…