arXiv subjects

Gou Tan

Publications and source records attributed to Gou Tan.

8 recordsLinked to original sources

arXiv2026

Understanding and Improving Model Editing for Secure Code Generation

Large language models (LLMs) are widely used for code generation, yet they can reproduce vulnerable implementations learned from insecure training patterns. Prior work has mainly explored inference-time hardening, which reduces insecure generations without modifying the target model but relies on auxiliary components and adds runtime overhead. We conduct the first systematic study of model editing as a model-level hardening mechanism for secure code generation. We evaluate 3 state-of-the-art editing methods across diverse LLM families and compare them with CoSec, a representative inference-time approach, focusing on security, robustness, generalization, and functional correctness. Model editing yields larger security gains than CoSec on seen vulnerability types, improving security ratios by 15%-25% over vanilla models, with gains remaining stable under prompt perturbations. However, these improvements transfer unreliably to unseen vulnerabilities and can reduce functional correctness. To mitigate this trade-off, we propose SafeEdit, a post-edit refinement method combining functional tuning with edit-aware regularization. Across eight target LLMs, SafeEdit improves Pass@1 over UltraEdit by 11.73/13.70/15.50 percentage points at T=0.1/0.4/0.8 while largely preserving security. Compared with CoSec, it achieves relative security-ratio gains of 7.54%-12.04%. Additional evaluation on CodeGuard+ confirms improved joint secure-and-correct generation. SafeEdit and CoSec are also complementary, and their combination can further improve security while maintaining strong functional correctness. Overall, our results provide evidence-backed guidance for applying model editing to secure code generation.

cs.CR↗

arXiv2026

AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection

Agent systems rely on LLM APIs for every response, but these APIs can return server errors, truncated responses, or corrupted content that propagates through downstream agents and causes task failure. Evaluating robustness under these faults is crucial for reliable deployment. Existing fault injection methods are offline, require source code modification, or cannot modify specific response fields. A comprehensive evaluation also requires a systematic fault taxonomy because different fault types affect downstream agents differently. We propose AgentChaos, a chaos engineering framework for controlled, runtime, non-intrusive LLM API fault injection. Since all agent systems access LLMs through the same HTTP interface, we inject faults at this shared layer without modifying source code. We define crash, omission, and value faults on content and tool call fields, intercept and modify LLM API responses at runtime, and verify whether each fault is triggered to filter untriggered tasks and avoid underestimating fault impact. Evaluations across agent systems, benchmarks, and backbone LLMs under 65 fault configurations show that all systems degrade under fault injection, with pass@1 dropping by up to 50 percentage points. The ranking is consistent across models, suggesting that robustness depends on system implementation rather than model capability. Existing fault diagnosis methods achieve below 53% accuracy on fault type and below 56% on fault step, leaving room for improvement. We further reveal practical findings for agent system developers.

cs.SE↗

arXiv2026

SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation

Large language models (LLMs) excel at general-purpose code generation, yet how well they handle scientific code remains an open question. Existing datasets and benchmarks are limited in scale, domain coverage, or executable verification, leaving the true gap between current LLMs and reliable scientific code generators inadequately assessed. To address these limitations, we present SciCodePile, the largest scientific code corpus to date, constructed from 37,737 public repositories and collectively comprising 128GB of code that spans multiple computational science disciplines. From this corpus, we further curate an executable benchmark of 200 tasks, each equipped with a sandboxed execution environment and an automated test harness for functional verification. We evaluate 15 LLMs from both open-source and closed-source families on three tasks: prefix-to-suffix completion, fill-in-the-middle infilling, and executable code generation. Results show that scientific code generation remains highly challenging: The best CodeBLEU reaches only 38.13 and 38.37 on the two completion tasks, while the strongest model achieves just 12.30\% Pass@1 on the executable benchmark, underscoring how far current models remain from reliable scientific code generation. To demonstrate the training utility of SciCodePile, we further show that continued pretraining on our corpus improves CodeBLEU by $\times$2.84 on scientific code completion, and instruction tuning on our data improves Pass@1 by $\times$4.79 on the executable benchmark. All code and data are available at https://huggingface.co/SciCodePile.

cs.SE↗

arXiv2026

OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning

In the field of software operations, Large Language Models (LLMs) have attracted increasing attention. However, existing research has not yet achieved efficient and effective endto-end intelligent operations due to low-quality data, fragmented knowledge and insufficient learning. To explore the potential of LLMs in software operations, we propose OpsLLM, a domainspecific LLM that supports both knowledge-based question answering (QA) and root cause analysis (RCA). Moreover, we disclose the detailed workflow for building LLMs specifically in the software operations domain. First, a Human-in-the-Loop mechanism is introduced to curate high-quality data from a large collection of operational data and construct a fine-tuning dataset. Then, based on the data, supervised fine-tuning is conducted to achieve a base model. Furthermore, we introduce a domain process reward model (DPRM) during the reinforcement learning stage to optimize the accuracy and reliability of the fine-tuned model on RCA tasks. Experimental results on the tasks with diverse difficulties demonstrate that OpsLLMs effectively learns and aligns with the operational domain knowledge infused, outperforming existing open-source and closed-source LLMs in accuracy with improvements of 0.2%~11.9% on QA tasks and 8.5%~70.3% on RCA tasks, while exhibiting strong transferability. Moreover, we will open-source three versions of OpsLLM with 7B, 14B and 32B parameters, along with a 15K fine-tuning dataset.

cs.LG↗

arXiv2026

MetaRCA: A Generalizable Root Cause Analysis Framework for Cloud-Native Systems Powered by Meta Causal Knowledge

The dynamics and complexity of cloud-native systems present significant challenges for Root Cause Analysis (RCA). While causality-based RCA methods have shown significant progress in recent years, their practical adoption is fundamentally limited by three intertwined challenges: poor scalability against system complexity, brittle generalization across different system topologies, and inadequate integration of domain knowledge. These limitations create a vicious cycle, hindering the development of robust and efficient RCA solutions. This paper introduces MetaRCA, a generalizable RCA framework for cloud-native systems. MetaRCA first constructs a Meta Causal Graph (MCG) offline, a reusable knowledge base defined at the metadata level. To build the MCG, we propose an evidence-driven algorithm that systematically fuses knowledge from Large Language Models (LLMs), historical fault reports, and observability data. When a fault occurs, MetaRCA performs a lightweight online inference by dynamically instantiating the MCG into a localized graph based on the current context, and then leverages real-time data to weight and prune causal links for precise root cause localization. Evaluated on 252 public and 59 production failures, MetaRCA demonstrates state-of-the-art performance. It surpasses the strongest baseline by 29 percentage points in service-level and 48 percentage points in metric-level accuracy. This performance advantage widens as system complexity increases, with its overhead scaling near-linearly. Crucially, MetaRCA shows robust cross-system generalization, maintaining over 80% accuracy across diverse systems.

cs.SE↗

arXiv2026

LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis

LLM-integrated software, which embeds or interacts with large language models (LLMs) as functional components, exhibits probabilistic and context-dependent behaviors that fundamentally differ from those of traditional software. This shift introduces a new category of integration defects that arise not only from code errors but also from misaligned interactions among LLM-specific artifacts, including prompts, API calls, configurations, and model outputs. However, existing defect localization techniques are ineffective at identifying these LLM-specific integration defects because they fail to capture cross-layer dependencies across heterogeneous artifacts, cannot exploit incomplete or misleading error traces, and lack semantic reasoning capabilities for identifying root causes. To address these challenges, we propose LIDL, a multi-agent framework for defect localization in LLM-integrated software. LIDL (1) constructs a code knowledge graph enriched with LLM-aware annotations that represent interaction boundaries across source code, prompts, and configuration files, (2) fuses three complementary sources of error evidence inferred by LLMs to surface candidate defect locations, and (3) applies context-aware validation that uses counterfactual reasoning to distinguish true root causes from propagated symptoms. We evaluate LIDL on 146 real-world defect instances collected from 105 GitHub repositories and 16 agent-based systems. The results show that LIDL significantly outperforms five state-of-the-art baselines across all metrics, achieving a Top-3 accuracy of 0.64 and a MAP of 0.48, which represents a 64.1% improvement over the best-performing baseline. Notably, LIDL achieves these gains while reducing cost by 92.5%, demonstrating both high accuracy and cost efficiency.

cs.SE↗

arXiv2025

InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching

Modern software systems generate massive volumes of runtime logs, necessitating efficient and accurate log parsing to enable critical downstream tasks such as anomaly detection and root cause analysis. Recently, large language models (LLMs) have achieved advanced accuracy on log parsing, but their deployment in production environments faces two major limitations: (1) the privacy risks associated with commercial LLMs, driving the adoption of local deployment, and (2) the stringent latency and throughput requirements imposed by high-volume log streams, which existing LLM-based parsers fail to meet. Although recent efforts have reduced the number of LLM queries, they overlook the high latency of the LLM invocations, where concurrent log parsing requests can cause serve performance degradation of LLM inference system. In this study, we present InferLog, the first LLM inference optimization method for online log parsing. Our key insight is that the inference efficiency emerges as the vital bottleneck in LLM-based online log parsing, rather than parsing accuracy. InferLog accelerates inference by designing (1) A Prefix-aware ICL Refinement policy to refine the examples and permutation of in-context learning to improve the prefix caching efficiency. (2) A rapid and task-specific configuration tuning pipeline based on meta-learning to find the optimal LLM scheduling-related configuration for dynamic log parsing workloads. The experimental results based on Loghub dataset and vLLM demonstrate that InferLog significantly outperforms existing inference optimization methods and markedly accelerates the state-of-the-art LLM-based log parser without compromising parsing accuracy.

cs.SE↗

arXiv2024

A Survey on Failure Analysis and Fault Injection in AI Systems

The rapid advancement of Artificial Intelligence (AI) has led to its integration into various areas, especially with Large Language Models (LLMs) significantly enhancing capabilities in Artificial Intelligence Generated Content (AIGC). However, the complexity of AI systems has also exposed their vulnerabilities, necessitating robust methods for failure analysis (FA) and fault injection (FI) to ensure resilience and reliability. Despite the importance of these techniques, there lacks a comprehensive review of FA and FI methodologies in AI systems. This study fills this gap by presenting a detailed survey of existing FA and FI approaches across six layers of AI systems. We systematically analyze 160 papers and repositories to answer three research questions including (1) what are the prevalent failures in AI systems, (2) what types of faults can current FI tools simulate, (3) what gaps exist between the simulated faults and real-world failures. Our findings reveal a taxonomy of AI system failures, assess the capabilities of existing FI tools, and highlight discrepancies between real-world and simulated failures. Moreover, this survey contributes to the field by providing a framework for fault diagnosis, evaluating the state-of-the-art in FI, and identifying areas for improvement in FI techniques to enhance the resilience of AI systems.

cs.SE↗