Search arXiv⌕ Search

arXiv subjects

Chunyang Chen

Publications and source records attributed to Chunyang Chen.

At least 19 recordsLinked to original sources
arXiv2026

Guidelines for Empirical Studies in Software Engineering involving Large Language Models

Large Language Models (LLMs) are widely used in software engineering (SE) research and practice, yet their non-determinism, opaque training data, and rapidly evolving models threaten the reproducibility and replicability of empirical studies. We address this challenge through a collaborative effort of 22 researchers, presenting a taxonomy of seven study types that organizes how LLMs are used in SE research, together with eight guidelines for designing and reporting such studies. Each guideline distinguishes requirements (must) from recommendations (should) and is contextualized by the study types it applies to. Our guidelines recommend that researchers: (1) declare LLM usage and role; (2) report model versions, configurations, and customizations; (3) document the system and prompt design beyond the model; (4) report session traces, i.e., interaction logs and runtime traces; (5) use suitable baselines, benchmarks, and metrics; (6) include an open LLM as a baseline; (7) validate LLM outputs against human judgment; and (8) articulate limitations and mitigations. We complement the guidelines with an applicability matrix mapping guidelines to study types and a reporting checklist for authors and reviewers. We maintain the study types and guidelines online as a living resource for the community to use and shape (llm-guidelines$.$org).

cs.SE↗
arXiv2026

SEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging

COBOL remains critical across banking, insurance, and government infrastructure. However, maintenance is increasingly challenging due to outdated technologies, sparse documentation, and developer retirement, necessitating code translation into modern languages like C. Traditional rule-based transcompilers yield outputs that are difficult to read and maintain, while general-purpose large language models (LLMs) achieve suboptimal correctness because COBOL is a low-resource language with distinct logic patterns. To bridge this gap, we propose SEDCoT, a novel COBOL-to-C translation framework. SEDCoT first leverages LLMs for initial translation, then combines symbolic execution with LLM guidance to generate test suites and iteratively repair semantic discrepancies. Finally, it integrates delta debugging to minimize failing tests into succinct counterexamples, accelerating automated code repair. Evaluating SEDCoT on a public COBOL-to-C dataset demonstrates that it outperforms state-of-the-art baselines by at least 12% while producing translations with substantially higher readability than rule-based alternatives.

cs.SE↗
arXiv2026

IFHierBench: Hierarchical Instruction Following for Large Language Models

Instruction-following ability is critical for deploying large language models in real-world applications, where downstream components depend on the output satisfying specific constraints. Modern deployments increasingly handle the full task in a single LLM call, with one prompt specifying a layered output whose overall artifact, structural sections, and nested fields must each satisfy concrete constraints. Existing instruction-following benchmarks treat the constraint set as a flat list applied uniformly to the response, so they cannot scope a check to a particular section of the output. We introduce IFHierBench, a hierarchical instruction-following benchmark of 600 prompts stratified across four constraint-tree depths and 35 distinct constraints, each prompt paired with a deterministic checker that verifies satisfaction at every scope. Evaluating seven leading proprietary and open-weight models, we find that even the strongest model only marginally exceeds 50% prompt-level accuracy and that accuracy degrades sharply as constraint depth grows. Reliably following nested constraints remains a substantial gap for current LLMs, motivating future training methods that consider constraint adherence at finer granularity to achieve better instruction-following ability.

cs.AI↗
arXiv2026

Bridging Stakeholder and Product Requirements: An Empirical Study of Requirement Engineering in the Automotive Industry

The automotive industry's shift toward software-driven systems has increased system complexity and raised the importance of effective requirement intake and refinement for correctness, compliance, development speed, and systematic reuse. Although prior research has proposed techniques for improving requirement quality, limited empirical evidence exists on how stakeholder-level requirements are evaluated, refined, and transformed into product-level requirements in industrial automotive practice. This paper presents a large-scale empirical study based on an industrial dataset from Infineon, comprising 8,082 stakeholder requirements and 5,870 product requirements enriched with traceability links, decision outcomes, deviation rationales, and domain references. Using a mixed-methods approach, we combine quantitative analyses of requirement structures, decision distributions, and mapping patterns with qualitative analyses of rationales, referenced specifications, and software- and hardware-related artifacts. We investigate structural and contextual differences between stakeholder and product requirements, factors influencing acceptance, rejection, and approval with deviation, and the nature of stakeholder-to-product refinement. The results reveal systematic differences across abstraction levels and show that refinement complexity is driven primarily by architectural scope and missing contextual information rather than linguistic verbosity. We further derive a taxonomy of stakeholder-product mapping patterns and relate these patterns to differing refinement effort. The findings provide concrete insight into industrial requirements intake and refinement practices and identify actionable opportunities for improving intake validation, deviation management, and tool-supported contextual enrichment to support faster and more reusable automotive product development.

cs.SE↗
arXiv2026

Beyond Textual Repository Exploration: Dual-Modal Structural Reasoning for Agentic Issue Resolution

Recent advances in agentic program repair have significantly improved issue resolution by enabling iterative repository exploration. However, existing approaches predominantly rely on sequential, text-based code navigation, which fundamentally limits their ability to reason over large-scale long-horizon repositories with complex and long-range dependencies. As issue-resolution agents traverse repositories through fragmented textual observations, structural information such as module organization, call relationships, and dependency chains must be repeatedly reconstructed across interaction steps, often leading to exploration drift and incomplete localization. We present DUALVIEW, a dual-modal structural scaffolding framework that brings visual reasoning into repository exploration for issue-resolution agents. DUALVIEW represents repository structure through four complementary graph views: Module Coupling Graph (MCG), Function Call Graph (FCG), Class Hierarchy Graph (CHG), and Program Dependence Graph (PDG), and exposes them through a queryable interface with visual and textual responses. Rather than reconstructing repository structure from a sequence of textual observations, agents can directly reason over persistent visual representations of code dependencies, enabling more effective exploration and understanding of long-horizon codebases. We evaluate DUALVIEW on SWE-bench Pro and Verified. Results show that DUALVIEW consistently improves issue-resolution performance across different agent architectures and model families. Further ablation studies demonstrate that the gains arise not only from textual structural information but also from visual externalization of repository dependencies, which better supports long-horizon repository exploration.

cs.SE↗
arXiv2026

SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models

Residual-stream analysis asks how language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates across layers. If embedding anchors and unembedding readout disagree on the chosen span, apparent motion may reflect measurement drift rather than computation. We introduce \emph{Semantic Reference Frames} (SemRF), an anchor-based formalism separating semantic measurement from residual dynamics. A SemRF fixes anchors and measures states against them. Pseudo-inverse tying gives exact synchronization; under restricted bi-invertibility, SemRF yields stable semantic-basis coordinates, distortion bounds, and near-identity changes. With the frame fixed, residual computation becomes a depthwise semantic trajectory. The anchors induce a semantic Voronoi diagram: distance, or evidence such as logits, assigns each layer to a coarse cell, while coordinates retain within-cell motion and margins. We define layerwise steps, contribution profiles, and imbalance diagnostics, then use the Voronoi trace to define a margin-relaxed tube. The canonical trace is the minimum-action path inside this tube; when nonempty with positive quadratic weight, it is unique and obeys a discrete spline equation away from active constraints. Excess action controls step, curvature, and profile mismatch. Low curvature implies piecewise-linear compressibility and local knowledge density: lower trace complexity means fewer semantic knots. Through the parameter-to-trajectory map, this gives a conditional link to parameter efficiency: among admissible settings fitting data, lower-action and lower-complexity traces use fewer semantic degrees of freedom. The guarantees require controlled interface error and small projection residual under explicit tube constraints.

cs.LG↗
arXiv2026

Large Language Models for Mobile GUI Text Input Generation: An Empirical Study

Mobile apps have become essential, making quality assurance increasingly important. GUI testing is widely used for automated exploration, yet text-input components remain a major obstacle, as many UI pages require semantically appropriate text inputs before proceeding. Large Language Models have shown promise in generating context-aware text, but the effectiveness of different UI representations, feedback mechanisms, and human intervention remains unclear. This paper presents a large-scale empirical study addressing these gaps. We evaluate nine state-of-the-art LLMs across 115 real-world apps, comparing three UI-context prompting settings: extracted textual context, UI-hierarchy XML, and screenshot-based vision input. Results show extracted context and XML achieve comparable page-pass-through rates of 71.4% and 71.0%, while vision-based input reaches 65.1% but incurs substantially higher token costs. In bug-detection experiments with 37 real-world text-input bugs, LLMs generating invalid inputs detect about 51% of issues across all evaluated models. A feedback-enhanced protocol, incorporating execution outcomes into subsequent attempts, improves average PPTRs to 69.2-73.8% and raises bug-detection rates to 51.0-64.5%. Human testers further refine inputs, yielding additional gains. We integrate the process into DroidBot, augmenting its UI-exploration capabilities. We derive actionable insights on context selection, cost-effectiveness, feedback strategies, and human-LLM collaboration, advancing both knowledge and practice in Android testing.

cs.SE↗
arXiv2026

Evaluating LLMs on Real-World Software Performance Optimization

Software performance optimization is a notoriously complex and manual task. Despite the growing use of Large Language Models (LLMs) for code refinement, we still lack benchmarks that capture how optimization actually happens in real-world codebases. Existing frameworks often oversimplify the problem by focusing on isolated functions or a single performance metric, missing the critical trade-offs between execution time and memory footprint, the inherent noise of the measurement environment, and the variability introduced by different input data and execution conditions. We address this by introducing SWE-Pro, a repository-level benchmark derived from 102 expert-written optimizations from open-source projects. Unlike previous benchmarks, SWE-Pro pairs each task with parameterized tests to evaluate runtime, peak memory, and Time-Weighted Memory Usage (TWMU) across varying input data and execution conditions under noise-aware measurement conditions. Our evaluation shows that current LLMs struggle significantly: runtime gains are negligible, and memory optimizations are nearly non-existent. This stands in sharp contrast to expert implementations, which achieve an aggregate speedup of 15.5x and peak memory reduction of 171.3x over benchmark tasks. Expert-written improvements are observed in 91.2% of tasks for runtime and 65.7% for peak memory. Our findings expose a substantial gap between current LLM capabilities and the demands of expert-level engineering.

cs.SE↗
arXiv2026

A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer Repair

Web accessibility (A11Y), which ensures web content is perceivable and usable for users with disabilities, is a critical requirement for modern web applications. Yet existing tooling overwhelmingly focuses on detecting A11Y violations rather than repairing them. Automated program repair (APR) techniques appear promising for this setting, but our study shows that state-of-the-art APR systems perform poorly when applied to real-world A11Y violations. Unlike conventional sparse-bug scenarios, web A11Y issues often manifest as multiple structurally related violations per page, requiring coordinated edits across multiple files. Existing repair systems fail to manage this multi-fault scale, as they handle each bug individually without considering their relationships or incorporating domain rules such as the Web Content Accessibility Guidelines (WCAG). We propose A11YRepair, an LLM-based framework for web A11Y repair. A11YRepair introduces a divide-and-conquer workflow that first clusters violations requiring coordinated edits to reduce redundant localization, and then decomposes each cluster by root cause so the LLM can generate focused and consistent patches. The framework further incorporates WCAG-driven knowledge to strengthen domain awareness during both fault localization and patch synthesis. To support systematic evaluation, we construct A11YBench, a benchmark of 60 real-world web projects collected from GitHub. Experimental results show that A11YRepair achieves higher repair effectiveness and lower cost than state-of-the-art baselines, and ablation studies confirm the importance of its divide-and-conquer design and selective domain knowledge integration. Specifically, patches generated by A11YRepair have been merged into open-source projects from Google, Microsoft, Facebook, IBM, K8s, Docker, and Alibaba, demonstrating its practical value.

cs.SE↗
arXiv2026

A Longitudinal Study of Android Apps Signing Key Protection

Android app signing relies on developer-managed credentials, making secure key protection essential for the integrity of the software supply chain. A recent platform key leakage incident involving two major OEM manufacturers demonstrates that even robustly designed signing mechanisms can be compromised due to developers' oversight. In this work, we conduct a longitudinal ecosystem study to characterize this threat by mining public repositories for Android signing credentials, recovering compromised keys via exposed passwords, and matching them against signatures from over 4,000 apps collected from major stores and OEM system images. Our analysis identifies 5,673 compromised keystores on GitHub and 26 unique certificates linked to 278 real-world apps. These include 26 third-party apps in public app stores and 252 preinstalled apps from seven manufacturers, collectively affecting over 10 billion users. We demonstrate the practical exploitability of these leaks through a proof-of-concept app replacement attack and identify spillover risks in non-smartphone platforms, including a popular automotive head-unit platform installed in over 1,100 vehicle models. Our results reveal that signing-key mismanagement is a systemic risk, underscoring the need for a more rigorous key-management support in Android release engineering and distribution infrastructures.

cs.CR↗
arXiv2026

Adoption of Generative Artificial Intelligence in the German Software Engineering Industry: An Empirical Study

Generative artificial intelligence (GenAI) tools have seen rapid adoption among software developers. While adoption rates in the industry are rising, the underlying factors influencing the effective use of these tools, including the depth of interaction, organizational constraints, and experience-related considerations, have not been thoroughly investigated. This issue is particularly relevant in environments with stringent regulatory requirements, such as Germany, where practitioners must address the GDPR and the EU AI Act while balancing productivity gains with intellectual property considerations. Despite the significant impact of GenAI on software engineering, to the best of our knowledge, no empirical study has systematically examined the adoption dynamics of GenAI tools within the German context. To address this gap, we present a comprehensive mixed-methods study on GenAI adoption among German software engineers. Specifically, we conducted 18 exploratory interviews with practitioners, followed by a developer survey with 109 participants. We analyze patterns of tool adoption, prompting strategies, and organizational factors that influence effectiveness. Our results indicate that experience level moderates the perceived benefits of GenAI tools, and productivity gains are not evenly distributed among developers. Further, organizational size affects both tool selection and the intensity of tool use. Limited awareness of the project context is identified as the most significant barrier. We summarize a set of actionable implications for developers, organizations, and tool vendors seeking to advance artificial intelligence (AI) assisted software development.

cs.SE↗
arXiv2026

Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment

Language Models (LMs) encode substantial knowledge in their parameters, yet it remains unclear how to transfer such knowledge in a fine-grained manner, namely parametric knowledge transfer (PKT). A central challenge is to make cross-scale transfer effective and efficient when source and target models differ in architecture and parameterization, making direct parameter reuse strongly limited by neural incompatibility. In this paper, we identify latent semantic alignment as the key prerequisite for cross-scale knowledge transfer. Instead of directly moving layer parameters, our approach uses activations as the transfer medium. \textsc{SemAlign} has two stages: an \emph{layer attribution} stage that attributes task-relevant source layers and selects exactly one source layer for each target layer, and a \emph{semantic alignment} stage that pairs them layer by layer and optimizes the target with source-side semantic supervision. The alignment is carried out in latent space through semantic decomposition and recomposition. During the shallow-to-deep transfer, only the frontier target layer is trainable. The layer objective supervises the residual contribution of that layer by matching centered token-token relation geometry against an aligned supervisory residual, while output KL preserves source-level predictive behavior. The transferred medium is therefore neither a parameter block nor an absolute hidden state, but target-space residual geometry induced by paired source-layer supervision. Evaluations on four benchmarks demonstrate the efficacy of \textsc{SemAlign}, and further analysis confirms that semantic decomposition and recomposition provide a stable mechanism for cross-scale knowledge transfer.

cs.CL↗
arXiv2026

Rethinking Weight Tying: Pseudo-Inverse Tying for LM Stable Training and Updates

Weight tying is widely used in compact language models to reduce parameters by sharing the token table between the input embedding and the output projection. However, parameter sharing alone does not guarantee a stable token interface: during training, the correspondence between encoding tokens into hidden states and decoding hidden states into logits can drift, worsening optimization sensitivity and weakening explainability probes that rely on a meaningful vocabulary-space decoder. We propose Pseudo-Inverse Tying (PIT), which synchronizes embedding and unembedding as coupled projections of a shared latent token memory, guaranteeing a pseudo-inverse-consistent interface throughout training. PIT maintains an orthonormal shared memory, obtained by polar initialization from a source checkpoint for continued pretraining or by random orthonormal initialization for from-scratch pretraining, and introduces a learned symmetric positive definite hidden-space transform parameterized via a Cholesky factor. The output head applies this transform to hidden states before the vocabulary projection, while the embedding applies the inverse transform to token vectors using stable triangular solves, avoiding explicit pseudo-inverse recomputation and vocabulary-sized auxiliary parameters. Beyond improving training stability, PIT provides a cleaner substrate for logit-lens-style and vocabulary-space explainability probes by keeping the input and output token geometries synchronized. We evaluate PIT on on-device models spanning 256M-1.3B parameters. The results show that PIT improves continued-pretraining stability, enforces near-exact token-interface consistency across settings, and yields more predictable lightweight adaptation after continued pretraining, while from-scratch pretraining reveals a trade-off between strict interface consistency and unconstrained optimization.

cs.CL↗
arXiv2026

Scenario-Guided LLM-based Mobile App GUI Testing

The assurance of mobile app GUI has become increasingly important, as the GUI serves as the primary medium of interaction between users and apps. Although numerous automated GUI testing approaches have been developed with diverse strategies, a substantial gap remains between these approaches and the underlying app business logic. Most existing approaches focus on general exploration rather than the completion of specific testing scenarios, often resulting in missed coverage of critical functionalities. Inspired by the manual testing process, which treats business logic, driven testing scenarios as the fundamental unit of testing, this paper introduces an approach that leverages large language models (LLMs) to comprehend the semantics expressed in app GUIs and their contextual relevance to given testing scenarios. Building upon this capability, we propose ScenGen, a novel scenario-guided LLM-based GUI testing framework that employs a multi-agent collaboration mechanism to simulate and automate the phases of manual testing. ScenGen integrates five agents. The Observer perceives the app GUI state by extracting and structuring GUI widgets and layouts, thereby interpreting the semantic information presented in the GUI. This information is then passed to the Decider, which makes scenario-driven decisions with the guidance of LLMs to identify target widgets and determine appropriate actions toward fulfilling specific testing goals. The Executor executes the decided operations on the app, while the Supervisor verifies whether the execution results align with the intended testing scenario completion, ensuring traceability and consistency in test generation and execution. Finally, the Recorder records the corresponding GUI operations into the context memory as a knowledge base for subsequent decision-making and concurrently monitors runtime bug occurrences.

cs.SE↗
arXiv2026

ViBR: Automated Bug Replay from Video-based Reports using Vision-Language Models

Bug reports play a critical role in software maintenance by helping users convey encountered issues to developers. Recently, GUI screen capture videos have gained popularity as a bug reporting artifact due to their ease of use and ability to retain rich contextual information. However, automatically reproducing bugs from such recordings remains a significant challenge. Existing methods often rely on fragile image-processing heuristics, explicit touch indicators, or pre-constructed UI transition graphs, which require non-trivial instrumentation and app-specific setup. This paper presents ViBR, a lightweight and fully automated approach that reproduces bugs directly from GUI recordings. Specifically, ViBR combines CLIP-based embedding similarity for action boundary segmentation with Vision-Language Models (VLMs) for region-aware GUI state comparison and guided bug replay. Experimental results show that ViBR successfully reproduces 72% of bug recordings, significantly outperforming state-of-the-art baselines and ablation variants.

cs.SE↗
arXiv2026

Towards Automated Crowdsourced Testing via Personified-LLM

The rapid proliferation and increasing complexity of software demand robust quality assurance, with graphical user interface (GUI) testing playing a pivotal role. Crowdsourced testing has proven effective in this context by leveraging the diversity of human testers to achieve rich, scenario-based coverage across varied devices, user behaviors, and usage environments. In parallel, automated testing, particularly with the advent of large language models (LLMs), offers significant advantages in controllability, reproducibility, and efficiency, enabling scalable and systematic exploration. However, automated approaches often lack the behavioral diversity characteristic of human testers, limiting their capability to fully simulate real-world testing dynamics. To address this gap, we present PersonaTester, a novel personified-LLM-based framework designed to automate crowdsourced GUI testing. By injecting representative personas, defined along three orthogonal dimensions: testing mindset, exploration strategy, and interaction habit, into LLM-based agents, PersonaTester enables the simulation of diverse human-like testing behaviors in a controllable and repeatable manner. Experimental results demonstrate that PersonaTester faithfully reproduces the behavioral patterns of real crowdworkers, exhibiting strong intra-persona consistency and clear inter-persona variability (117.86% -- 126.23% improvement over the baseline). Moreover, persona-guided testing agents consistently generate more effective test events and trigger more crashes (100+) and functional bugs (11) than the baseline without persona, thus substantially advancing the realism and effectiveness of automated crowdsourced GUI testing.

cs.SE↗
arXiv2026

Exploring MLLMs Perception of Network Visualization Principles

In this paper, we test whether Multimodal Large Language Models (MLLMs) can match human-subject performance in tasks involving the perception of properties in network layouts. Specifically, we replicate a human-subject experiment about perceiving quality (namely stress) in network layouts using GPT-4o, Gemini-2.5 and Qwen2.5. Our experiments show that giving MLLMs the same study information as trained human participants yields performance comparable to that of human experts and exceeds that of untrained non-experts. Additionally, we show that prompt engineering that deviates from the human-subject experiment can lead to better-than-human performance in some settings. Interestingly, like human subjects, the MLLMs seem to rely on visual proxies rather than computing the actual value of stress, indicating some sense or facsimile of perception. Explanations from the models are similar to those used by the human participants (e.g., an even distribution of nodes and uniform edge lengths).

cs.HC↗
arXiv2026

RippleGUItester: Change-Aware Exploratory Testing

Software systems evolve continuously through frequent code changes, yet such changes often introduce unintended bugs despite extensive testing and code review. Existing testing approaches are largely constrained to predefined execution paths or rely on unguided exploration, leaving many change-induced issues undetected. To address this challenge, we present RippleGUItester, a change-driven testing system that treats a code change as the epicenter of a ripple effect and explores its broader, user-visible impacts via the GUI. Given a code change, RippleGUItester performs LLM-based change-impact analysis to generate and enrich realistic test scenarios, executes these scenarios on both pre-change and post-change versions of the system, and applies differential analysis to identify behavioral differences. Crucially, RippleGUItester employs multimodal bug detection, comparing visual GUI changes and interpreting them in the context of natural-language change intents to distinguish unintended bugs from intended behavioral updates. We evaluate our approach on hundreds of real-world code changes across four widely used software systems: Firefox, Zettlr, JabRef, and Godot. Our results show that the proposed approach uncovers bugs introduced by code changes that were missed by existing test suites, CI pipelines, and code review. In total, we identify 26 previously unknown bugs that still exist in the latest versions of the evaluated systems. After reporting, 16 bugs have been fixed, 2 have been confirmed, 6 are still under discussion, and 2 were marked as intended. We envision RippleGUItester being applied before or shortly after a code change is merged, enabling earlier detection of regressions.

cs.SE↗