arXiv subjects

Hailu Xu

Publications and source records attributed to Hailu Xu.

7 recordsLinked to original sources

arXiv2026

Leveraging Resolved Incident History for LLM-Assisted Software Bug Diagnosis

Effective software bug diagnosis requires two ingredients: the right knowledge source (operational failure history, not just system documentation) and the right retrieval structure (structured records, not unstructured chunks). Current retrieval-augmented generation (RAG) approaches fall short on one or both dimensions. We propose Operational Memory RAG (OM-RAG), which indexes resolved issues as structured symptom-root cause-resolution triples and retrieves the most similar historical precedent via single-hop embedding. OM-RAG powers a purpose-built large language model (LLM) administrator that has operated a production Dataverse instance for over six months, operationalizing the Knowledge component of the Monitor-Analyze-Plan-Execute-Knowledge (MAPE-K) feedback loop with the system's own resolved failure history. In a controlled four-configuration ablation, LLM-based judging covers all 1,172 issues and manual verification a 123-issue subset. OM-RAG achieves Diagnosis Accuracy of 0.931 and Fix Correctness of 0.809, outperforming chunk-based retrieval (+186%) and a documentation-anchored concept graph (+77%). Model-free retrieval metrics (mean similarity 0.880) independently corroborate the ranking.

cs.SE↗

arXiv2026

Cross-Model LLM Code Review: Should you use Claude to review Codex or vice versa?

Developers increasingly use two coding agents together: one writes a draft, and the other reviews it. However, it is not clear whether the pairing is worth its cost and time, or whether the order of the pairing matters. We run a controlled experiment on 116 recent hard and medium lcb tasks with Claude and Codex across six conditions to approximate a software practitioner's workflow: both solo baselines, both cross-model orderings, and both same-model orderings. The reviewer sees the problem and the writer's draft but cannot execute tests, which approximates a code review step. Claude review raises Codex drafts from 71.6% to 89.7% ($p_{BH}=.001$); Codex self review raises them to 84.5% ($p_{BH}=.022$). The reverse direction does not pay off: Codex reviewing Claude drafts drops the pass rate from 91.4% to 82.8% ($p_{BH}=.046$), and Claude self review leaves the 91.4% baseline unchanged. Our evaluation indicates that the useful pairing is asymmetric: use Claude to review Codex, not the other way around.

cs.SE↗

arXiv2026

SwiftBot: A Decentralized Platform for LLM-Powered Federated Robotic Task Execution

Federated robotic task execution systems require bridging natural language instructions to distributed robot control while efficiently managing computational resources across heterogeneous edge devices without centralized coordination. Existing approaches face three limitations: rigid hand-coded planners requiring extensive domain engineering, centralized coordination that contradicts federated collaboration as robots scale, and static resource allocation failing to share containers across robots when workloads shift dynamically. We present SwiftBot, a federated task execution platform that integrates LLM-based task decomposition with intelligent container orchestration over a DHT overlay, enabling robots to collaboratively execute tasks without centralized control. SwiftBot achieves 94.3% decomposition accuracy across diverse tasks, reduces task startup latency by 1.5-5.4x and average training latency by 1.4-2.5x, and improves tail latency by 1.2-4.7x under high load through federated warm container migration. Evaluation on multimedia tasks validates that co-designing semantic understanding and federated resource management enables both flexibility and efficiency for robotic task control.

cs.RO↗

arXiv2025

Pronunciation Deviation Analysis Through Voice Cloning and Acoustic Comparison

This paper presents a novel approach for detecting mispronunciations by analyzing deviations between a user's original speech and their voice-cloned counterpart with corrected pronunciation. We hypothesize that regions with maximal acoustic deviation between the original and cloned utterances indicate potential mispronunciations. Our method leverages recent advances in voice cloning to generate a synthetic version of the user's voice with proper pronunciation, then performs frame-by-frame comparisons to identify problematic segments. Experimental results demonstrate the effectiveness of this approach in pinpointing specific pronunciation errors without requiring predefined phonetic rules or extensive training data for each target language.

cs.SD↗

arXiv2024

StraightLine: An End-to-End Resource-Aware Scheduler for Machine Learning Application Requests

The life cycle of machine learning (ML) applications consists of two stages: model development and model deployment. However, traditional ML systems (e.g., training-specific or inference-specific systems) focus on one particular stage or phase of the life cycle of ML applications. These systems often aim at optimizing model training or accelerating model inference, and they frequently assume homogeneous infrastructure, which may not always reflect real-world scenarios that include cloud data centers, local servers, containers, and serverless platforms. We present StraightLine, an end-to-end resource-aware scheduler that schedules the optimal resources (e.g., container, virtual machine, or serverless) for different ML application requests in a hybrid infrastructure. The key innovation is an empirical dynamic placing algorithm that intelligently places requests based on their unique characteristics (e.g., request frequency, input data size, and data distribution). In contrast to existing ML systems, StraightLine offers end-to-end resource-aware placement, thereby it can significantly reduce response time and failure rate for model deployment when facing different computing resources in the hybrid infrastructure.

cs.DC↗

arXiv2023

Improving CNN-base Stock Trading By Considering Data Heterogeneity and Burst

In recent years, there have been quite a few attempts to apply intelligent techniques to financial trading, i.e., constructing automatic and intelligent trading framework based on historical stock price. Due to the unpredictable, uncertainty and volatile nature of financial market, researchers have also resorted to deep learning to construct the intelligent trading framework. In this paper, we propose to use CNN as the core functionality of such framework, because it is able to learn the spatial dependency (i.e., between rows and columns) of the input data. However, different with existing deep learning-based trading frameworks, we develop novel normalization process to prepare the stock data. In particular, we first empirically observe that the stock data is intrinsically heterogeneous and bursty, and then validate the heterogeneity and burst nature of stock data from a statistical perspective. Next, we design the data normalization method in a way such that the data heterogeneity is preserved and bursty events are suppressed. We verify out developed CNN-based trading framework plus our new normalization method on 29 stocks. Experiment results show that our approach can outperform other comparing approaches.

q-fin.ST↗

arXiv2022

Making Machine Learning Datasets and Models FAIR for HPC: A Methodology and Case Study

The FAIR Guiding Principles aim to improve the findability, accessibility, interoperability, and reusability of digital content by making them both human and machine actionable. However, these principles have not yet been broadly adopted in the domain of machine learning-based program analyses and optimizations for High-Performance Computing (HPC). In this paper, we design a methodology to make HPC datasets and machine learning models FAIR after investigating existing FAIRness assessment and improvement techniques. Our methodology includes a comprehensive, quantitative assessment for elected data, followed by concrete, actionable suggestions to improve FAIRness with respect to common issues related to persistent identifiers, rich metadata descriptions, license and provenance information. Moreover, we select a representative training dataset to evaluate our methodology. The experiment shows the methodology can effectively improve the dataset and model's FAIRness from an initial score of 19.1% to the final score of 83.0%.

cs.LG↗