arXiv subjects

Zhenxi Chen

Publications and source records attributed to Zhenxi Chen.

5 recordsLinked to original sources

arXiv2026

WebDesignIter: Co-Evolving Design Knowledge for Repository-Level Front-End Code Generation

Front-end development accumulates change after change at the repository level, weaving complex cross-file dependencies that current LLM coding agents tuned for single-shot tasks cannot reliably track across multiple iterations, leading to functional regressions and code that resists maintenance. We argue the missing piece is design knowledge: architectural principles, module responsibilities, and structural constraints that developers lean on to keep code readable, maintainable, and evolvable as a system scales. To operationalize this, we propose WebDesignIter, a framework built around a persistent knowledge graph (WebAppArchKG) that fuses repository structure with design knowledge and keeps both in sync across development cycles. WebDesignIter works in two stages: design-informed planning pulls historical context and architectural overviews from WebAppArchKG to produce an implementation plan with corresponding test scripts, and design-aware generation executes that plan through targeted diff-based patches, validated by sandbox execution and automatic syntax repair. On Web-Bench, WebDesignIter delivers an average Pass@2 gain of 9.55 percentage points across nine foundation models over existing baselines. More importantly, WebDesignIter outperforms every general-purpose coding agent Claude Code, OpenHands, SWE-Agent, Codex CLI on every model configuration, posting the highest Pass@1 and Pass@2 while consuming 2530 fewer input tokens. Ablation singles out design knowledge as the most impactful component: stripping it drops Pass@1 by 11.40 percentage points, a degradation far larger than removing code-graph retrieval, patch-based generation, or sandbox verification, confirming that design knowledge provides a fundamentally more efficient and reliable path to repository-level code generation.

cs.SE↗

arXiv2026

Dynamic analysis enhances issue resolution

Resolving complex code defects from natural language descriptions remains a fundamental software engineering challenge. Recently, large language models (LLMs) have driven the creation of agent-based automated repair systems. While improving repository-level problem-solving, current methods struggle with complex defects like intricate polymorphic control flows and implicit type degradation. These approaches rely on static analysis and shallow execution feedback, lacking the ability to monitor intermediate execution states. Consequently, agents often fall into speculative exploration, consuming significant tokens without identifying the root cause. We introduce DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent), a pioneering automated repair framework deeply embedding dynamic analysis into the agent's decision loop. DAIRA employs a Test Tracing-Driven workflow, using lightweight tools to capture runtime evidence (e.g., call stacks and variable states) and convert it into structured semantic reports. By illuminating execution paths and causal dependencies, DAIRA enables precise fault localization and prevents context window flooding from irrelevant code retrievals. This shifts the agent's approach from speculative reasoning to deterministic inference. Evaluations on the SWE-bench Verified benchmark show DAIRA achieves a state-of-the-art 79.4% resolution rate when powered by Gemini 3 Flash Preview. Furthermore, it demonstrates robustness in addressing deep-seated logical defects, securing a 44.4% resolution rate on the most demanding tasks. Compared to baselines, DAIRA uniquely resolves complex edge cases and improves operational efficiency. Across various LLMs, it reduces inference costs by approximately 10% and input token consumption by 25%.

cs.SE↗

arXiv2026

Knowledge Matters: Injecting Project and Testing Knowledge into LLM-based Unit Test Generation

Automated unit test generation using large language models (LLMs) holds great promise but often struggles with generating tests that are both correct and maintainable in real-world projects. This paper presents KTester, a novel framework that integrates project-specific knowledge and testing domain knowledge to enhance LLM-based test generation. Our approach first extracts project structure and usage knowledge through static analysis, which provides rich context for the model. It then employs a testing-domain-knowledge-guided separation of test case design and test method generation, combined with a multi-perspective prompting strategy that guides the LLM to consider diverse testing heuristics. The generated tests follow structured templates, improving clarity and maintainability. We evaluate KTester on multiple open-source projects, comparing it against state-of-the-art LLM-based baselines using automatic correctness and coverage metrics, as well as a human study assessing readability and maintainability. Results demonstrate that KTester significantly outperforms existing methods across six key metrics, improving execution pass rate by 5.69% and line coverage by 8.83% over the strongest baseline, while requiring less time and generating fewer test cases. Human evaluators also rate the tests produced by KTester significantly higher in terms of correctness, readability, and maintainability, confirming the practical advantages of our knowledge-driven framework.

cs.SE↗

arXiv2026

Architecture-Aware Multi-Design Generation for Repository-Level Feature Addition

Implementing new features across an entire codebase presents a formidable challenge for Large Language Models (LLMs). This proactive task requires a deep understanding of the global system architecture to prevent unintended disruptions to legacy functionalities. Conventional pipeline and agentic frameworks often fall short in this area because they suffer from architectural blindness and rely on greedy single-path code generation. To overcome these limitations, we propose RAIM, a multi-design and architecture-aware framework for repository-level feature addition. This framework introduces a localization mechanism that conducts multi-round explorations over a repository-scale code graph to accurately pinpoint dispersed cross-file modification targets. Crucially, RAIM shifts away from linear patching by generating multiple diverse implementation designs. The system then employs a rigorous impact-aware selection process based on static and dynamic analysis to choose the most architecturally sound patch and avoid system regressions. Comprehensive experiments on the NoCode-bench Verified dataset demonstrate that RAIM establishes a new state-of-the-art performance with a 39.47% success rate, achieving a 36.34% relative improvement over the strongest baseline. Furthermore, the approach exhibits robust generalization across various foundation models and empowers open-weight models like DeepSeek-v3.2 to surpass baseline systems powered by leading proprietary models. Detailed ablation studies confirm that the multi-design generation and impact validation modules are critical to effectively managing complex dependencies and reducing code errors. These findings highlight the vital role of structural awareness in automated software evolution.

cs.SE↗

arXiv2025

Generating High-Quality Datasets for Code Editing via Open-Source Language Models

Code editing plays a vital role in software engineering, requiring developers to adjust existing code according to natural language instructions while keeping functionality intact and avoiding unnecessary modifications. However, commit-based datasets commonly used for this task are often noisy, lack diversity, and fail to reflect the style of real-world edit instructions. To address this, we introduce OpenCodeEdit, an open-source pipeline that leverages multiple LLMs to synthesize realistic code-edit triplets. The pipeline produces both concise "lazy" instructions and more detailed "descriptive" ones, and applies filtering based on diffs and topics to guarantee data quality and variety. Using this process, we construct OCEDataFT, a curated dataset of 20K samples. Fine-tuning three advanced base models on OCEDataFT leads to significant performance boosts on the CanItEdit benchmark, with relative pass@1 improvements ranging from 4.50% to 20.79%. Notably, the resulting models achieve performance close to closed-source systems, narrowing the gap to GPT-4 to just 3.54%, without relying on proprietary resources or manual annotation.

cs.SE↗