arXiv subjects

Yakun Zhang

Publications and source records attributed to Yakun Zhang.

At least 19 recordsLinked to original sources

arXiv2026

MADE: Belief-Driven Dual-Agent Coordination for Autonomous Model Deployment

LLM-based agents now have strong general capabilities. However, they still struggle with domain-specific tasks, motivating the integration of external tools to broaden their capabilities. The open-source community offers a vast array of AI models typically released as heterogeneous research artifacts, whereas transforming them into ready-to-call APIs is costly and labor-intensive. Automated model deployment is therefore essential for bridging the gap between model resources and tool usability, yet it remains a long-horizon, multi-stage task that has not been sufficiently explored. To tackle this challenge, we introduce Model Automated Deployment Engine (MADE), a dual-agent coordination system. Specifically, given a model resource, MADE iteratively constructs and validates the deployment artifacts, updates its deployment belief based on execution feedback, and revisits invalid upstream artifacts until the model is successfully served as a ready-to-call API that can then be used by other agents. We further introduce M2ABench, a benchmark for the task of transforming Models to ready-to-call APIs. M2ABench comprises 122 real-world models with standardized test cases for evaluation. Experimental results demonstrate that MADE achieves a deployment success rate of 68.85%, outperforming SWE-agent and OpenHands by 13.93 and 44.26 percentage points, respectively. Our code and dataset are publicly available at https://github.com/HITDiSC/MADE.

cs.SE↗

arXiv2026

TraceDev: A Traceability-Driven Multi-agent Framework for Requirement-to-Code Development

In modern software development, the rapid advancement of Large Language Models (LLMs) has made the end-to-end transformation of Natural Language Requirements (NLRs) into executable repository-level code increasingly feasible. However, existing approaches typically rely on simplified instructions (e.g., single-sentence descriptions), failing to reflect complex software development scenarios. Moreover, they lack explicit requirement traceability mechanisms, making it difficult to precisely align and validate generated code against original requirements. To address these limitations, we propose TraceDev, a multi-agent framework for automated software development grounded in use cases that contain multiple functional points and complex semantics. TraceDev employs five role-specific agents, including a Requirement Refiner, Designer, Developer, Tester, and Validator. Notably, the Validator Agent constructs and maintains a heterogeneous traceability graph that links requirements, design models, and code artifacts for interacting with the preceding four agents. The traceability graph maintains consistency across various artifacts and serves as a structured context for efficient memory management, supporting reliable repository-level code generation. We evaluate TraceDev on two widely used datasets (including 125 use cases) compared with two state-of-the-art approaches. On the ETOUR dataset, TraceDev achieves a success rate of 53.63\%, outperforming baseline approaches by up to 186.63\%. A similar trend is observed on the SMOS dataset, where TraceDev attains a success rate of 56.82\%, exceeding baseline approaches by up to 340.80\%. These results demonstrate the effectiveness of TraceDev in repository-level code generation from requirements.

cs.SE↗

arXiv2026

LogiDroid: Individual Functional Test Generation via Business Logic Extraction and Adaptation

Functional testing is essential for verifying that the business logic of mobile applications aligns with user requirements. Despite its importance, functional testing remains heavily dependent on manual effort due to two core challenges. First, acquiring and reusing business logic from unstructured requirements remains difficult, which hinders the understanding of specific functionalities. Second, a significant semantic gap exists when adapting business logic to the diverse GUI environments, which hinders the generation of test cases for specific mobile applications. To address the preceding challenges, we propose LogiDroid, a two-stage approach that generates individual functional test cases by extracting business logic and adapting it to target applications. First, in the Knowledge Retrieval and Fusion stage, two LLM-based agents are employed to construct a functional test dataset, retrieve relevant test cases, and extract structured business logic for the target functionality. Second, in the Context-Aware Test Generation stage, two other LLM-based agents jointly analyze the extracted business logic and the real time GUI environment to incrementally generate context adaptive functional test cases. This design allows LogiDroid to accurately understand application semantics and use domain expertise to generate complete test cases with verification assertions. We assess the effectiveness of LogiDroid using two widely-used datasets that cover 28 real-world applications and 190 functional requirements. Experimental results show that LogiDroid successfully tested 40% of functional requirements on the FrUITeR dataset (an improvement of over 25% compared to the state-of-the-art approaches) and 65% on the Lin dataset (an improvement of over 55% compared to the state-of-the-art approaches). These results demonstrate the significant effectiveness of LogiDroid in functional test generation.

cs.SE↗

arXiv2026

An Empirical Study for Android-to-OpenHarmony GUI Test Migration

To reduce the substantial engineering effort required to test the corresponding applications from Android to OpenHarmony, migrating existing GUI test cases has become a critical problem. However, current research neither proposes solutions tailored for OpenHarmony nor provides a systematic evaluation of migration approaches on this system, leaving developers with limited empirical guidance in practice. In this paper, we present the first systematic empirical study of test migration from Android to OpenHarmony. Specifically, we first construct a dataset referred to as the ATH Benchmark, comprising 36 commercial applications with an average of over 9 billion downloads, along with 108 manually designed test cases. Second, we select two state-of-the-art test migration approaches (i.e., ReSPlay and ITeM) and adapt these two approaches to enable their execution on OpenHarmony. Third, we use the preceding infrastructure to evaluate these two approaches from three perspectives, including testing performance, root causes of failures, and the impact of OpenHarmony characteristics. Our results reveal that existing test migration approaches are less effective (15% success-rate on ReSPlay and 26% success-rate on ITeM) in Android-to-OpenHarmony scenarios. Through an in-depth analysis of failed cases, we identify that test performance is primarily hindered by OpenHarmony-specific characteristics, including technical architecture differences and unique ecosystem traits. Utilizing these findings, we propose an enhanced approach based on ITeM, referred as ITeM-HM, which incorporates specific OpenHarmony system features. As a result, ITeM-HM successfully achieves a 214% success-rate relative improvement over the original ITeM (from 26% to 81%).

cs.SE↗

arXiv2026

Contextualized Code Pretraining for Code Generation

As code generation becomes increasingly central to improving software development efficiency, modern code models are largely trained and evaluated on code with natural-language descriptions. In real projects, developers often implement missing functions under limited project-specific artifacts, while the local call-site context is already available in the surrounding code. This usage context provides actionable cues about expected behavior, but existing models are not explicitly optimized to leverage it reliably, leading to implementations that may not integrate smoothly with surrounding usage in repository settings. In this work, we propose contextualized code pretraining, an invocation-aware framework that integrates calling context into both the training and evaluation of code models. Using static analysis, we automatically extract large-scale caller-callee pairs from real repositories to construct pretraining tasks and benchmarks that condition generation on the calling context. We train CallerGen, the first code models pretrained with invocation-aware objectives spanning multiple sizes, and evaluate them on CallerEval, a new benchmark featuring realistic scenarios. Experiments show that CallerGen outperforms comparable-scale models and remains competitive with larger ones across two benchmarks. Our 220M and 0.5B models achieve 16.58% and 22.81@% pass1, surpassing baselines on CallerEval. These results highlight the importance of calling context in realistic code generation.

cs.SE↗

arXiv2026

Toward Executable Repository-Level Code Generation via Environment Alignment

Large language models (LLMs) have achieved strong performance on code generation, but existing methods still struggle with repository-level code generation under executable validation. Under this evaluation setting, success is determined not by the plausibility of isolated code fragments, but by whether a generated multi-file repository can be successfully installed, have its dependencies and internal references resolved, be launched, and be validated in a real execution environment. To address this challenge, we propose EnvGraph, a framework for repository-level code generation that formulates repository executability as an environment alignment problem. EnvGraph jointly models two coupled conditions for successful repository execution, namely external dependency satisfaction and repository-internal reference resolution. It maintains a dual-layer environment representation, uses execution evidence to perform execution-evidence-based attribution, and guides repository generation through a unified targeted revision mechanism within an iterative alignment loop. We evaluate EnvGraph on repository-level code generation with three representative backbone LLMs and compare it against representative environment-aware and repository-level baselines. Experimental results show that EnvGraph consistently achieves the best performance on these repository-level benchmarks. In particular, it outperforms the strongest non-EnvGraph baseline by an absolute margin of 5.72--5.87 percentage points in Functional Correctness and 4.58--8.66 percentage points in Non-Functional Quality.

cs.SE↗

arXiv2026

Persistent Cross-Attempt State Optimization for Repository-Level Code Generation

Large language models (LLMs) have achieved substantial progress in repository-level code generation. However, solving the same repository-level task often requires multiple attempts, while existing methods still optimize each attempt in isolation and do not preserve or reuse task-specific state across attempts. In this paper, we propose LiveCoder, a novel framework for repository-level code generation based on cross-attempt knowledge optimization. LiveCoder maintains persistent task-specific state from prior attempts to guide subsequent generation. This state includes success knowledge, which captures reusable signals from previously strong repositories, failure knowledge, which records unsuccessful outcomes and their diagnostic signals, and a historical-best repository, which preserves the strongest result found so far and prevents regression. These components collectively transform repeated repository generation into a persistent, knowledge-driven optimization process. We evaluate LiveCoder using four frontier LLMs on two representative repository-level code generation benchmarks. Extensive experimental results demonstrate the effectiveness and efficiency of LiveCoder, improving the functional score by up to 22.94 percentage points, increasing repository reuse to 81.58%, and reducing cost by up to 53.63% on RAL-Bench while maintaining broadly stable non-functional quality.

cs.SE↗

arXiv2026

Toward Functional and Non-Functional Evaluation of Application-Level Code Generation

Large language models (LLMs) have achieved strong performance on code generation. However, most prior evaluations focus on snippet-level outputs, such as function generation or repository completion. These settings do not fully evaluate application-level code generation, where the goal is to produce a runnable repository with coherent multi-file structure, dependency support, and end-to-end executability. In addition, real-world software quality depends not only on functional correctness but also on non-functional quality attributes, such as maintainability and security. In this paper, we present RAL-Bench, a benchmark and evaluation framework for application-level code generation. For each task, RAL-Bench derives a concise natural-language requirement from a high-quality reference project, constructs black-box system tests for both functional correctness and non-functional quality attributes. It also retains only the candidate tests that pass on the reference repository. Under this unified evaluation protocol, functional correctness is measured by the system test pass rate, while non-functional quality is evaluated along five ISO/IEC 25010-inspired dimensions, with per-dimension diagnostics and reference-normalized scoring.We evaluate 16 frontier LLMs under a controlled zero-shot setting with greedy decoding. The results show that functional correctness remains the primary bottleneck in application-level code generation, while non-functional quality also remains challenging. Under our evaluation protocol, no model exceeds a 45\% functional score. These findings suggest that strong performance on existing code generation benchmarks does not yet translate to strong performance on application-level repository generation. This result highlights the need for evaluation settings that directly assess end-to-end repository generation rather than relying only on snippet-level success.

cs.SE↗

arXiv2026

Why Database Manuals Are Not Enough: Efficient and Reliable Configuration Tuning for DBMSs via Code-Driven LLM Agents

Modern database management systems (DBMSs) expose hundreds of configuration knobs that critically influence performance. Existing automated tuning methods either adopt a data-driven paradigm, which incurs substantial overhead, or rely on manual-driven heuristics extracted from database documentation, which are often limited and overly generic. Motivated by the fact that the control logic of configuration knobs is inherently encoded in the DBMS source code, we argue that promising tuning strategies can be mined directly from the code, uncovering fine-grained insights grounded in system internals. To this end, we propose SysInsight, a code-driven database tuning system that automatically extracts fine-grained tuning knowledge from DBMS source code to accelerate and stabilize the tuning process. SysInsight combines static code analysis with LLM-based reasoning to identify knob-controlled execution paths and extract semantic tuning insights. These insights are then transformed into quantitative and verifiable tuning rules via association rule mining grounded in tuning observations. During online tuning, system diagnosis is applied to identify critical knobs, which are adjusted under the rule guidance. Evaluations demonstrate that compared to the SOTA baseline, SysInsight converges to the best configuration on average 7.11X faster while achieving a 19.9% performance improvement.

cs.DB↗

arXiv2026

A general Mayer-Vietoris sequence in algebraic $K$-theory

This paper investigates the Mayer-Vietoris sequence for the Milnor square. While such sequences often involve elusive intermediate terms, we provide an explicit characterization of the key group $X$ in a new, more general variant of the sequence. By identifying $X$ as a categorical pullback, we provide a full, constructive proof of the modified Mayer-Vietoris sequence. Furthermore, we show that $X$ fits into a structural exact sequence involving the relative $K$-groups $K_{*}(A, B, I)$. Finally, we provide a homotopy-theoretic description of $X$ as the homotopy group of a suitable fiber, clarifying its structure, kernel , and image.

math.KT↗

arXiv2026

Purification Before Fusion: Toward Mask-Free Speech Enhancement for Robust Audio-Visual Speech Recognition

Audio-visual speech recognition (AVSR) typically improves recognition accuracy in noisy environments by integrating noise-immune visual cues with audio signals. Nevertheless, high-noise audio inputs are prone to introducing adverse interference into the feature fusion process. To mitigate this, recent AVSR methods often adopt mask-based strategies to filter audio noise during feature interaction and fusion, yet such methods risk discarding semantically relevant information alongside noise. In this work, we propose an end-to-end noise-robust AVSR framework coupled with speech enhancement, eliminating the need for explicit noise mask generation. This framework leverages a Conformer-based bottleneck fusion module to implicitly refine noisy audio features with video assistance. By reducing modality redundancy and enhancing inter-modal interactions, our method preserves speech semantic integrity to achieve robust recognition performance. Experimental evaluations on the public LRS3 benchmark suggest that our method outperforms prior advanced mask-based baselines under noisy conditions.

eess.AS↗

arXiv2026

DBMIF: a deep balanced multimodal iterative fusion framework for air- and bone-conduction speech enhancement

The performance of conventional speech enhancement systems degrades sharply in extremely low signal-to-noise ratio (SNR) environments where air-conduction (AC) microphones are overwhelmed by ambient noise. Although bone-conduction (BC) sensors offer complementary, noise-tolerant information, existing fusion approaches struggle to maintain consistent performance across a wide range of SNR conditions. To address this limitation, we propose the Deep Balanced Multimodal Iterative Fusion Framework (DBMIF), a three-branch architecture designed to reconstruct high-fidelity speech through rigorous cross-modal interaction. Specifically, grounded in a multi-scale interactive encoder-decoder backbone, the framework orchestrates an iterative attention module and a cross-branch gated module to facilitate adaptive weighting and bidirectional exchange. To complement this dynamic interaction, a balanced-interaction bottleneck is further integrated to learn a compact, stable fused representation. Extensive experiments demonstrate that DBMIF achieves competitive performance compared with recent unimodal and multimodal baselines in both speech quality and intelligibility across diverse noise types. In downstream ASR tasks, the proposed method reduces the character error rate by at least 2.5 percent compared to competing approaches. These results confirm that DBMIF effectively harnesses the robustness of BC speech while preserving the naturalness of AC speech, ensuring reliability in real-world scenarios. The source code is publicly available at github.com/wyl516w/dbmif.

eess.AS↗

arXiv2026

One Decomposition of $K_2$-Group for Certain Quotients over $\mathbb{Z}[G]$ with $G$ a Finite Abelian $p$-Group

This paper investigates the structure of $K_2$-groups for certain quotient rings of the integral group ring $\mathbb{Z}[G]$. Let $G$ be a finite abelian $p$-group with $p$-rank $r$, let $Γ$ be the maximal $\mathbb{Z}$-order of $\mathbb{Q}[G]$, and let $\widetilde{G}$ denote the sum of all elements of $G$ in the group ring. By employing the framework of Kähler differentials, we first determine that the relative $K$-group $K_2(\mathbb{F}_p[G], (\widetilde{G}))$ is an elementary abelian $p$-group of rank $r$ when $|G|>2$. Building upon this result, we establish an explicit isomorphism for $r > 1$: $$ K_2(\mathbb{Z}[G]/(|G|Γ\cap p\mathbb{Z}[G])) \cong K_2(\mathbb{Z}[G]/|G|Γ) \oplus K_2(\mathbb{F}_p[G], (\widetilde{G})). $$

math.KT↗

arXiv2026

Explicit $K_2$ of certain quotient rings over $\mathbb{Z}[G]$ for $G$ an elementary abelian $p$-group

Let $G$ be an elementary abelian $p$-group. In this paper, we calculate the $K_2$-groups of some quotient rings $\mathbb{Z}[G]/I$ for certain ideals $I \subseteq \mathbb{Z}[G]$ of finite $p$-power index. These results are established through the explicit computation of Dennis-Stein symbols. As an application, we provide a definitive characterization of the relative group $SK_1(\mathbb{Z}[G], p^k\mathbb{Z}[G])$ for any odd prime $p$ and $k \ge 1$.

math.KT↗

arXiv2026

Computations of $K_2$ for certain $\mathbb{Z}/p^s\mathbb{Z}$-algebras and the extension of Oliver's logarithm

This paper describes the $K$-theory structure for three algebra classes. For cyclic $p$-group rings and truncated polynomial rings over $\mathbb{Z}/p^s\mathbb{Z}$, we determine reduced $K_2$-structures via a common algebraic framework. For abelian $p$-group rings over $\widehat{\mathbb{Z}}_p$, we extend the isomorphism between reduced continuous $K_2$ and the first cyclic homology group to all finite abelian $p$-groups. A constructive proof using a generalized Artin-Hasse map yields an explicit splitting. This isomorphism is realized by extending Oliver's $p$-adic logarithm. We also characterize the map from reduced continuous $K_2$ to reduced linearized $K_2$, clarifying the links between $K_2$, cyclic homology, and Kähler differentials.

math.KT↗

arXiv2025

CupCleaner: A Hybrid Data Cleaning Approach for Comment Updating

Comment updating is an emerging task in software evolution that aims to automatically revise source code comments in accordance with code changes. This task plays a vital role in maintaining code-comment consistency throughout software development. Recently, deep learning-based approaches have shown great potential in addressing comment updating by learning complex patterns between code edits and corresponding comment modifications. However, the effectiveness of these learning-based approaches heavily depends on the quality of training data. Existing datasets are typically constructed by mining version histories from open-source repositories such as GitHub, where there is often a lack of quality control over comment edits. As a result, these datasets may contain noisy or inconsistent samples that hinder model learning and generalization. In this paper, we focus on cleaning existing comment updating datasets, considering both the data's characteristics in the updating scenario and their implications on the model training process. We propose a hybrid statistical approach named CupCleaner (Comment UPdating's CLEANER) to achieve this purpose. Specifically, we combine static semantic information within data samples and dynamic loss information during the training process to clean the dataset. Experimental results demonstrate that, on the same test set, both the individual static strategy and the dynamic strategy can significantly filter out a portion of the data and enhance the performance of the model. Furthermore, employing a model ensemble approach can combine the characteristics of static and dynamic cleaning, further enhancing the performance of the model and the reliability of its output results.

cs.SE↗

arXiv2025

GUI Test Migration via Abstraction and Concretization

GUI test migration aims to produce test cases with events and assertions to test specific functionalities of a target app. Existing migration approaches typically focus on the widget-mapping paradigm that maps widgets from source apps to target apps. However, since different apps may implement the same functionality in different ways, direct mapping may result in incomplete or buggy test cases, thus significantly impacting the effectiveness of testing target functionality and the practical applicability of migration approaches. In this paper, we propose a new migration paradigm (i.e., the abstraction-concretization paradigm) that first abstracts the test logic for the target functionality and then utilizes this logic to generate the concrete GUI test case. Furthermore, we introduce MACdroid, the first approach that migrates GUI test cases based on this paradigm. Specifically, we propose an abstraction technique that utilizes source test cases from source apps targeting the same functionality to extract a general test logic for that functionality. Then, we propose a concretization technique that utilizes the general test logic to guide an LLM in generating the corresponding GUI test case (including events and assertions) for the target app. We evaluate MACdroid on two widely-used datasets (including 31 apps, 34 functionalities, and 123 test cases). On the FrUITeR dataset, the test cases generated by MACdroid successfully test 64% of the target functionalities, improving the baselines by 191%. On the Lin dataset, MACdroid successfully tests 75% of the target functionalities, outperforming the baselines by 42%. These results underscore the effectiveness of MACdroid in GUI test migration.

cs.SE↗

arXiv2025

AVE Speech: A Comprehensive Multi-Modal Dataset for Speech Recognition Integrating Audio, Visual, and Electromyographic Signals

The global aging population faces considerable challenges, particularly in communication, due to the prevalence of hearing and speech impairments. To address these, we introduce the AVE speech, a comprehensive multi-modal dataset for speech recognition tasks. The dataset includes a 100-sentence Mandarin corpus with audio signals, lip-region video recordings, and six-channel electromyography (EMG) data, collected from 100 participants. Each subject read the entire corpus ten times, with each sentence averaging approximately two seconds in duration, resulting in over 55 hours of multi-modal speech data per modality. Experiments demonstrate that combining these modalities significantly improves recognition performance, particularly in cross-subject and high-noise environments. To our knowledge, this is the first publicly available sentence-level dataset integrating these three modalities for large-scale Mandarin speech recognition. We expect this dataset to drive advancements in both acoustic and non-acoustic speech recognition research, enhancing cross-modal learning and human-machine interaction.

cs.SD↗