arXiv subjects

Yongxin Zhao

Publications and source records attributed to Yongxin Zhao.

7 recordsLinked to original sources

arXiv2026

QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation

Large Language Models (LLMs) have made significant progress in reasoning, particularly in deductive reasoning, which is crucial for high-stakes decision-making. As models improve, evaluation benchmarks should evolve to keep pace. However, existing benchmarks lack fine-grained control over logical complexity and struggle to balance semantic diversity with logical consistency. To address these issues, we propose QMFOL, an automated framework for generating monadic first-order logic reasoning tasks with quantifiable and controllable complexity. It constructs formal logical structures using conjunction and disjunction patterns, enabling precise control over reasoning depth, width, label types, and distractors. These structures are then translated into natural language via LLMs, with logical consistency ensured through round-trip verification using an external prover. Based on our framework, we build QMFOLBench, a benchmark comprising 2880 instances with 960 configurations across diverse logical and semantic dimensions. Evaluations on six large reasoning models (LRMs) and two LLMs show that performance degrades and computational overhead increases with rising logical complexity. Models perform better on True-labeled tasks than on False or Unknown ones, and exhibit sensitivity to semantic variation. Overall, QMFOL offers a scalable and reliable approach for constructing deductive reasoning benchmarks with controllable complexity, enabling more precise evaluation of reasoning capabilities in modern language models.

cs.AI↗

arXiv2026

R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling

Function calling empowers large language models (LLMs) to interface with external tools, yet existing RL-based approaches suffer from misalignment between reasoning processes and tool-call decisions. We propose R2IF, a reasoning-aware RL framework for interpretable function calling, adopting a composite reward integrating format/correctness constraints, Chain-of-Thought Effectiveness Reward (CER), and Specification-Modification-Value (SMV) reward, optimized via GRPO. Experiments on BFCL/ACEBench show R2IF outperforms baselines by up to 34.62% (Llama3.2-3B on BFCL) with positive Average CoT Effectiveness (0.05 for Llama3.2-3B), enhancing both function-calling accuracy and interpretability for reliable tool-augmented LLM deployment.

cs.LG↗

arXiv2026

Which Types of Heterogeneity Matter for Root Cause Localization in Microservice Systems ?

Microservice root cause localization is fundamentally challenged by the inherent heterogeneity of cloud-native systems, which encompasses diverse observability data and multiple system entities. Existing approaches typically focus on only one aspect of heterogeneity and thus fail to capture its full diagnostic value. In this work, we systematically examine the multifaceted role of heterogeneity within both microservice systems and the RCL process. This analysis motivates a deeper investigation into how entity-level distinctions and their asymmetric dependencies influence fault behavior. Our empirical analysis of two microservice benchmarks reveals that entity-level heterogeneity naturally gives rise to heterogeneous fault propagation, which is highly asymmetric and dominated by cross-layer interactions between services and hosts. In light of this, we propose NexusRCL, a semi-supervised framework that internalizes these propagation patterns by formalizing services and hosts as distinct node types within a heterogeneous graph. This design, coupled with an event-based abstraction mechanism, allows NexusRCL to effectively capture both data level and entity-level heterogeneity while minimizing labeling costs through active learning. Comprehensive evaluations on two industrial benchmark datasets demonstrate NexusRCL's superior performance, achieving improvements of up to 49.85\% in Top-1 accuracy (A@1) and 32.70\% in Average Top-5 accuracy (A@5) compared to state-of-the-art methods.

cs.SE↗

arXiv2026

STEAMROLLER: A Multi-Agent System for Inclusive Automatic Speech Recognition for People who Stutter

People who stutter (PWS) face systemic exclusion in today's voice-driven society, where access to voice assistants, authentication systems, and remote work tools increasingly depends on fluent speech. Current automatic speech recognition (ASR) systems, trained predominantly on fluent speech, fail to serve millions of PWS worldwide. We present STEAMROLLER, a real time system that transforms stuttered speech into fluent output through a novel multi-stage, multi-agent AI pipeline. Our approach addresses three critical technical challenges: (1) the difficulty of direct speech to speech conversion for disfluent input, (2) semantic distortions introduced during ASR transcription of stuttered speech, and (3) latency constraints for real time communication. STEAMROLLER employs a three stage architecture comprising ASR transcription, multi-agent text repair, and speech synthesis, where our core innovation lies in a collaborative multi-agent framework that iteratively refines transcripts while preserving semantic intent. Experiments on the FluencyBank dataset and a user study demonstrates clear word error rate (WER) reduction and strong user satisfaction. Beyond immediate accessibility benefits, fine tuning ASR on STEAMROLLER repaired speech further yields additional WER improvements, creating a pathway toward inclusive AI ecosystems.

cs.CY↗

arXiv2025

Triage in Software Engineering: A Systematic Review of Research and Practice

As modern software systems continue to grow in complexity, triage has become a fundamental process in system operations and maintenance. Triage aims to efficiently prioritize, assign, and assess issues to ensure the reliability of complex environments. The vast amount of heterogeneous data generated by software systems has made effective triage indispensable for maintaining reliability, facilitating maintainability, and enabling rapid issue response. Motivated by these challenges, researchers have devoted extensive effort to advancing triage automation and have achieved significant progress over the past two decades. This survey provides a comprehensive review of 234 papers from 2004 to the present, offering an in-depth examination of the fundamental concepts, system architecture, and problem statement. By comparing the distinct goals of academic and industrial research and by analyzing empirical studies of industrial practices, we identify the major obstacles that limit the practical deployment of triage systems. To assist practitioners in method selection and performance evaluation, we summarize widely adopted open-source datasets and evaluation metrics, providing a unified perspective on the measurement of triage effectiveness. Finally, we outline potential future directions and emerging opportunities to foster a closer integration between academic innovation and industrial application. All reviewed papers and projects are available at https://github.com/AIOps-Lab-NKU/TriageSurvey.

cs.SE↗

arXiv2025

Conformance Testing of Relational DBMS Against SQL Specifications

A Relational Database Management System (RDBMS) is one of the fundamental software that supports a wide range of applications, making it critical to identify bugs within these systems. There has been active research on testing RDBMS, most of which employ crash or use metamorphic relations as the oracle. Although existing approaches can detect bugs in RDBMS, they are far from comprehensively evaluating the RDBMS's correctness (i.e., with respect to the semantics of SQL). In this work, we propose a method to test the semantic conformance of RDBMS i.e., whether its behavior respects the intended semantics of SQL. Specifically, we have formally defined the semantics of SQL and implemented them in Prolog. Then, the Prolog implementation serves as the reference RDBMS, enabling differential testing on existing RDBMS. We applied our approach to four widely-used and thoroughly tested RDBMSs, i.e., MySQL, TiDB, SQLite, and DuckDB. In total, our approach uncovered 19 bugs and 11 inconsistencies, which are all related to violating the SQL specification or missing/unclear specification, thereby demonstrating the effectiveness and applicability of our approach.

cs.DB↗

arXiv2014

Bright and fast voltage reporters across the visible spectrum via electrochromic FRET (eFRET)

We present a palette of brightly fluorescent genetically encoded voltage indicators (GEVIs) with excitation and emission peaks spanning the visible spectrum, sensitivities from 6 - 10% Delta F/F per 100 mV, and half-maximal response times from 1 - 7 ms. A fluorescent protein is fused to an Archaerhodopsin-derived voltage sensor. Voltage-induced shifts in the absorption spectrum of the rhodopsin lead to voltage-dependent nonradiative quenching of the appended fluorescent protein. Through a library screen, we identified linkers and fluorescent protein combinations which reported neuronal action potentials in cultured rat hippocampal neurons with a single-trial signal-to-noise ratio from 6.6 to 11.6 in a 1 kHz imaging bandwidth at modest illumination intensity. The freedom to choose a voltage indicator from an array of colors facilitates multicolor voltage imaging, as well as combination with other optical reporters and optogenetic actuators.

q-bio.BM↗