Software System Performance and Reliability

Últimos artículos

• Counterexamples to Local Reconstruction Gain as a Proxy for Final Fidelity in Residual Completion

  Yasuto Hoshi, Daisuke Miyashita, Jun Deguchi · 30 de septiembre de 2026

  Residual completion augments query-aware sparse attention by estimating the contribution of tokens omitted from the exact sparse computation. We ask whether improving a layer's attention-output reconstruction on the same incoming Q/K/V and selected support necessarily improves the fidelity of the fi…

• REFINE: A Resilient Evolution Framework for Intelligent Enterprise Alert Triage in Security Operations Centers

  Huimin Chen, Quan Long, Yanhao Wang · 29 de septiembre de 2026

  Security Operations Centers (SOCs) process large volumes of alerts daily. Alert triage prioritizes high-risk threats while reducing manual review of benign alerts. LLM agents can reason over logs and threat intelligence, but struggle to keep aligned with organization-specific, rapidly evolving SOC o…

• STAR: Adaptive Spatial-Temporal Normalization for Unified Microservice Incident Management

  Xinhua Miao, Linyu Zhu, Bowei Yang, Zhengong Cai · 29 de septiembre de 2026

  Automated incident management in large-scale microservice systems relies on learning robust representations from multimodal observability data, including metrics, logs, and traces. Although recent self-supervised frameworks enable unified modeling for anomaly detection (AD), failure triage (FT), and…

• Are Benchmarks Reliable? Toward Structural Diagnosis via Sample-Level Capability Boundaries

  Haiquan Hu, Yuzhu Liang, Weicheng Tang, Yanzeng Li, Yao Shi, Tian Wang · 29 de septiembre de 2026

  Evaluating large language models (LLMs) relies heavily on benchmark scores, yet aggregate metrics can obscure whether benchmark samples reliably support model comparison. We introduce \textbf{BSDProbe}, a sample-level framework for \emph{benchmark structural diagnosis} that estimates capability boun…

• SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents

  Yifang Tian, Yingjian Bai, Yifeng He, Zichun Chong, Yuanchen Gao, Yiran Li, Hans-Arno Jacobsen · 29 de septiembre de 2026

  Benchmarks for site reliability engineering (SRE) agents are typically episodic: one fault is injected, the agent receives an incident task, and its response is scored. Production operation is not. Incidents surface through noisy alerts, overlap in time, and often originate from code or configuratio…

• From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis

  Shu-Xun Yang, Yidong Wang, Zhuoer Feng, Bosi Wen, Jiayi Gui, Dayong Yang, Wenbo Yu, Haoke Zhang, Jie Tang, Cunxiang Wang · 29 de septiembre de 2026

  LLM-driven agents are increasingly deployed in complex applications, where long agentic traces make failures difficult to diagnose. Existing trace diagnosis methods often conflate anomalies, errors, and failures, making diagnostic targets ambiguous; they also lack structured modeling of how causally…

• DAAF: From Failure Localization to Editable System Assets in LLM Agents

  Xiaoyang Yuan, Qi Liu, Yubin Ruan, Xinyi Mou, Zhuomeng Zhang, Wenjin Wang, Hanying Jiao, Di Wu, Mingye Xu, Yi Bin, Ke Feng, Zixun Sun · 29 de septiembre de 2026

  Deployed LLM agents increasingly rely on persistent, versioned system assets such as routing rules, knowledge segments, prompt instructions, and reusable skills. Failure-localization methods can identify where an error manifests in an agent or execution trace, but repair requires a different decisio…

• Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness

  Bin Li, Dongdong Wang, Siyang Lu · 28 de septiembre de 2026

  Large language models (LLMs) have demonstrated promising performance in log anomaly detection, yet how their adaptation strategies, architectures, and deployment configurations affect detection effectiveness remains insufficiently understood. To investigate these factors, we conduct a systematic emp…

• Learning to Remember: Attentive Reinforcement Learning for Edge Serverless Autoscaling

  Faraz Shaikh, Gianluca Reali, Mauro Femminella · 24 de septiembre de 2026

  In edge computing, the stochastic and bursty nature of serverless workloads challenges autonomous resource orchestration. Traditional reactive controllers, such as the Kubernetes Horizontal Pod Autoscaler (HPA), suffer from reaction latency, leading to Service Level Objective (SLO) violations during…

• Does Graph Structure Earn Its Place in Microservice Root-Cause Analysis? A Controlled Study on RCAEval, and What the Benchmark Was Really Measuring

  Imad Bulji\'c · 24 de septiembre de 2026

  Graph neural networks dominate recent work on microservice root-cause analysis, yet recent results question whether the graph contributes. Those results compare whole pipelines, so when a flat model wins one cannot tell whether structure is useless or redundant. We run the comparison they imply on R…

• Trains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers

  Weihang Ding, Junfei Zhan · 23 de septiembre de 2026

  Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned, evaluated, and deployed model under a budget, a human-approval gate, and reproducibility requirements. Seating an LLM agent in the FDE seat raises a …

• When Are Aggregate Agent Traces Diagnosable? Traffic-Governed Interpretation and Calibrated Abstention

  Peiying Zhu, Sidi Chang · 23 de septiembre de 2026

  Runtime traces can appear transparent, but a closed-loop policy determines which states are visited and which failures become visible. We study a simulated hotel-pricing agent mapping time, inventory, and market state to discrete price actions under varying demand regimes. A fault may leave no aggre…

• ARID: A Deployable Edge AI System for Structured Information Extraction from Industrial Maintenance Work Orders

  Kuanlin Chen, Chen-Wei Kuo · 22 de septiembre de 2026

  Maintenance work orders must often be processed offline on embedded hardware, yet downstream software requires predictable structured output. We present ARID (Aviation-inspired Routing for Industrial Deployment), which extracts component, failure mode, symptom, and maintenance action into fixed-sche…

• Towards Secure Cloud-Native Computing: Unveiling Kubernetes Misconfigurations with Large Language Models

  Mostafa Anouar Ghorab, Mohamed Aymen Saied · 21 de septiembre de 2026

  In the rapidly evolving landscape of cloud-native computing, Organizations are increasingly adopting infrastructure models that emphasize scalability, flexibility, and efficiency. Kubernetes has become the de facto standard for orchestrating containerized applications in these environments. However,…

• BurnRiSc: Toward Non-Invasive Burnout Screening in Open Source from Public Repository Signals

  Timofey Sanko, Yuan Tian, Mariam Guizani · 18 de septiembre de 2026

  Burnout is a chronic occupational syndrome, and open source is close to a worst case for it: maintainers absorb unbounded demand with no manager to reallocate work and no organization to notice decline. The cost is not only personal. Burnout precedes withdrawal, and in projects sustained by a handfu…

• TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOps

  Rohit Patel, Susil Kumar Mohanty, Jeenal Chaudhary · 15 de septiembre de 2026

  Cloud-hosted large language models (LLMs) are increasingly used for root cause analysis (RCA) in AIOps pipelines, but they introduce data privacy risk, network latency, and per-query cost that scale poorly with production log volumes. We present TriCalRAG, a benchmark evaluating open-weight LLMs ser…

• Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures

  Harsh Raj, David Lee, Anas Mahmoud, Renxiong Wang, Razvan-Gabriel Dumitru, Chenguang Wang, Tong Zhao, Yunzhong He, Darvin Yi, Vipul Gupta · 15 de septiembre de 2026

  The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reliability, as it transforms outcome-level signals into actionable interventions. The sheer scale of the data renders human review impractical, driving…

• DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems

  Zehao Wang, Lanjun Wang, Shilong Jin, Junjie Chen, Yanghua Xiao · 7 de septiembre de 2026

  Large language model (LLM)-based multi-agent systems have experienced rapid growth in recent years. Despite their promise, such systems remain fragile, frequently exhibiting reasoning and coordination errors that can lead to system-level failures. Failure attribution in such systems relies on tracin…

• SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center

  Uday Vallabhaneni, Cassie L. Cagwin, David J. Wild · 4 de septiembre de 2026

  Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, but two limitations make them unreliable at enterprise scale: a finite context window cannot hold a multi-thousand-host authentication graph, and free-form generation offers no guarantee that a recommended contai…

• Large Language Models (LLMs) for Telecom Root Cause Analysis (RCA): A Structured Reasoning Framework for Evidence-Grounded Diagnosis

  Hao Zhou (Jianzhong), Mandar Kulkarni (Jianzhong), Hao Chen (Jianzhong), Yan Xin (Jianzhong), Charlie (Jianzhong), Zhang · 3 de septiembre de 2026

  Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing performance degradations in modern 5G and emerging 6G networks remains challenging due to complex cross-layer dependencies. While large language models (LLMs) offer promising capabilities for reasoning and kno…

• Loom: Weaving Diagnostic Strands into Free-Text Consensus via Embedding-Space Reweighting

  Ron Begleiter, Katya Egert Berg, Gilad Saban, Gil Shabat · 3 de septiembre de 2026

  Aggregating noisy, conflicting textual hypotheses into a reliable consensus is a fundamental challenge when deploying NLP systems in real-world industrial settings. While monolithic Large Language Model (LLM) agents offer unbounded expressivity for tasks like Root Cause Analysis (RCA), they suffer f…

• Semantic Signal-Assisted Inspection and Recovery Allocation in Reverse Logistics

  Jiani He, Dingyan Shang, Yihua Xu, Shiqi Huang, Yan Lyu, Jize Li, Shangjing Tang · 3 de septiembre de 2026

  Reverse-logistics operators often decide how to inspect and route returned assets before their condition is fully observed, while full inspection consumes scarce labor. Semantic Signal-Assisted Decision Support converts return notes into a condition factor and a signal-quality score that guide inspe…

• EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems

  Jun Hou, Priya Pitre, Yi Fang, Xuan Wang · 2 de septiembre de 2026

  Large language model (LLM) agent failures often contain multiple related errors rather than a single mistake. Existing attribution methods usually identify a responsible agent, step, or root cause, but do not explicitly model dependency between errors. We introduce EDGE, an Error Dependency Graph-gu…

• PolicyLong: Towards On-Policy Context Extension

  Junlong Jia, Jiang Zhou, Ziyang Chen, Xing Wu, Chaochen Gao, TingHao Yu, Feng Zhang, Songlin Hu · 31 de agosto de 2026

  Extending LLM context windows is hindered by scarce high-quality long-context data. Recent methods synthesize data with genuine long-range dependencies via information-theoretic verification, selecting contexts that reduce a base model's predictive entropy. However, their single-pass offline constru…

• FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets

  Kuan-Hao Tseng, Niruth Bogahawatta, Yasod Ginige, Kunjan Patel, Kosta Dakic, Suranga Seneviratne · 28 de agosto de 2026

  LLM-based agents are increasingly proposed for network fault diagnosis, but existing benchmarks evaluate them only on accurate tickets and always assume a fault is present, conditions rarely met in practice. We present FaulT-Bench, a benchmark of 200 troubleshooting scenarios across eight network to…