Related papers: STAR: A Stage-attributed Triage and Repair framewo…
Large language model (LLM) services have become an integral part of search, assistance, and decision-making applications. However, unlike traditional web or microservices, the hardware and software stack enabling LLM inference deployment is…
As comprehensive large model evaluation becomes prohibitively expensive, predicting model performance from limited observations has become essential. However, existing statistical methods struggle with pattern shifts, data sparsity, and…
Large language model (LLM) agents frequently fail on multi-step tasks involving reasoning, tool use, and environment interaction. While such failures are typically logged or retried heuristically, they contain structured signals about where…
As contemporary microservice systems become increasingly popular and complex-often comprising hundreds or even thousands of fine-grained, interdependent subsystems-they are facing more frequent failures. Ensuring system reliability thus…
As modern microservice systems grow increasingly complex due to dynamic interactions and evolving runtime environments, they experience failures with rising frequency. Ensuring system reliability therefore critically depends on accurate…
Root cause analysis (RCA) in microservices is challenging due to (i) noisy and heterogeneous multimodal observability (metrics, logs, traces), (ii) cascading failure propagation that amplifies downstream symptoms, and (iii) non-stationary…
While cloud-native microservice architectures have revolutionized software development, their inherent operational complexity makes failure Root Cause Analysis (RCA) a critical yet challenging task. Numerous data-driven RCA models have been…
Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks. Despite the successes of chain-of-thought and tree-based search methods, they mainly depend on the internal…
Detecting failures and identifying their root causes promptly and accurately is crucial for ensuring the availability of microservice systems. A typical failure troubleshooting pipeline for microservices consists of two phases: anomaly…
The complex dependencies and propagative faults inherent in microservices, characterized by a dense network of interconnected services, pose significant challenges in identifying the underlying causes of issues. Prompt identification and…
Partial differential equation (PDE) foundation models are pretrained networks that forecast how physical fields like velocity and pressure evolve from a single reusable solver. On unfamiliar flows their predictions drift step by step,…
Large Language Model (LLM) inference has emerged as a fundamental paradigm, however, variations in output length cause severe workload imbalance in the decode phase, particularly for long-output reasoning tasks. Existing systems, such as PD…
Multi-Agent Reinforcement Learning (MARL) is increasingly deployed in safety-critical domains, yet methods for interpretable failure detection and attribution remain underdeveloped. We introduce a two-stage gradient-based framework that…
Large Language Model (LLM)-based Multi-Agent Systems (MAS) enable complex problem-solving but introduce significant debugging challenges, characterized by long interaction traces, inter-agent dependencies, and delayed error manifestation.…
Retrieval-Augmented Generation (RAG) is widely employed to mitigate risks such as hallucinations and knowledge obsolescence in medical question answering, yet its predominantly single-round, static retrieval paradigm misaligns with the…
Implementing large language models (LLMs)-driven root cause analysis (RCA) in cloud-native systems has become a key topic of modern software operations and maintenance. However, existing LLM-based approaches face three key challenges:…
Table reasoning with large language models (LLMs) plays a critical role in building intelligent systems capable of understanding and analyzing tabular data. Despite recent progress, existing methods still face key limitations: their…
A simultaneously transmitting and reflecting intelligent surface (STARS) enabled integrated sensing and communications (ISAC) framework is proposed, where the whole space is divided by STARS into a sensing space and a communication space. A…
Continuous Integration and Deployment (CI/CD) pipelines are critical to modern software engineering, yet diagnosing and resolving their failures remains complex and labor-intensive. We present LogSage, the first end-to-end LLM-powered…
To assist IT service developers and operators in managing their increasingly complex service landscapes, there is a growing effort to leverage artificial intelligence in operations. To speed up troubleshooting, log anomaly detection has…