Related papers: OpsAgent: An Evolving Multi-agent System for Incid…
Mobile GUI agents exhibit substantial potential to facilitate and automate the execution of user tasks on mobile phones. However, exist mobile GUI agents predominantly privilege autonomous operation and neglect the necessity of active user…
Automated incident management plays a pivotal role in large-scale microservice systems. However, many existing methods rely solely on single-modal data (e.g., metrics, logs, and traces) and struggle to simultaneously address multiple…
As the complexity of the HPC storage stack rapidly grows, domain scientists face increasing challenges in effectively utilizing HPC storage systems to achieve their desired I/O performance. To identify and address I/O issues, scientists…
The past two years have witnessed the evolution of large language model (LLM)-based multi-agent systems from labor-intensive manual design to partial automation (\textit{e.g.}, prompt engineering, communication topology) and eventually to…
Large language models (LLMs) are increasingly grounded in sensor data to perceive and reason about human physiology and the physical world. However, accurately interpreting heterogeneous multimodal sensor data remains a fundamental…
The adoption of large language models (LLMs) in healthcare has attracted significant research interest. However, their performance in healthcare remains under-investigated and potentially limited, due to i) they lack rich domain-specific…
Crisis management is a complex problem raised by the scientific community currently. Decision support systems are a suitable solution for such issues, they are indeed able to help emergency managers to prevent and to manage crisis in…
Multimodal large language models (MLLMs) have shown remarkable capability in bridging visual perception and textual reasoning, enabling zero-shot understanding across diverse industrial scenarios. However, their performance in…
The application of language models to project-level vulnerability detection remains challenging, owing to the dual requirement of accurately localizing security-sensitive code and correctly correlating and reasoning over complex program…
AI agents are entering high-risk production settings, where they use tools, retain context, follow policies, handle private data, and interact with users over multiple turns. Yet many evaluation methods still judge isolated outputs or…
Modern artificial intelligence relies on networks of agents that collect data, process information, and exchange it with neighbors to collaboratively solve optimization and learning problems. This article introduces a novel distributed…
In the realm of microservices architecture, the occurrence of frequent incidents necessitates the employment of Root Cause Analysis (RCA) for swift issue resolution. It is common that a serious incident can take several domain experts hours…
Recently, Agentic AI has become an increasingly popular research field. However, we argue that current agent research practices lack standardization and scientific rigor, making it hard to conduct fair comparisons among methods. As a…
Evaluation insights are limited by the availability of high-quality benchmarks. As models evolve, there is a need to create benchmarks that can measure progress on new and complex generative capabilities. However, manually creating new…
This paper introduces a multi-agent application system designed to enhance office collaboration efficiency and work quality. The system integrates artificial intelligence, machine learning, and natural language processing technologies,…
Modern scientific research relies on large-scale data, complex workflows, and specialized tools, which existing LLMs and tool-based agents struggle to handle due to limitations in long-horizon planning, robust goal maintenance, and…
Data incompleteness severely impedes the reliability of multimodal systems. Existing reconstruction methods face distinct bottlenecks: conventional parametric/generative models are prone to hallucinations due to over-reliance on internal…
As data continues to grow in scale and complexity, preparing, transforming, and analyzing it remains labor-intensive, repetitive, and difficult to scale. Since data contains knowledge and AI learns knowledge from it, the alignment between…
Analyzing whole-slide images (WSIs) requires an iterative, evidence-driven reasoning process that parallels how pathologists dynamically zoom, refocus, and self-correct while collecting the evidence. However, existing computational…
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,…