arXiv subjects

Xin Xia

Publications and source records attributed to Xin Xia.

At least 19 recordsLinked to original sources

arXiv2026

Unsaid, Unsafe? Implicit Security Obligations in LLM-Based RTL Code Generation

Large Language Models (LLMs) generate register-transfer-level (RTL) code with rapidly improving functional correctness. Security of LLM-generated code, however, has been studied mainly for software, where flaws can still be patched after deployment. Insecure RTL offers no such remedy once taped out into silicon. We construct SECRTL-GEN, a multi-language resource-access security benchmark grounded in real SoC IP: 392 tasks over five CWE families and four HDLs (Verilog, SystemVerilog, VHDL, and Python), each with black-box functional and security testbenches. Functional specifications intentionally omit security obligations, matching how obligations are often kept out of functional docs in practice. An empirical study of five frontier LLMs shows a sharp gap: under vanilla prompts they pass functional tests in about 73-79% of cases but security tests in only 14-35%, and stronger functional models are not safer. Adding CWE knowledge raises security, while unaided self-thinking helps less and both security-oriented prompts cut functional pass rates, showing that the bottleneck is missing weakness awareness in the specification, not an inability to write defensive RTL. We present RTL-Obliger, a neuro-symbolic framework that infers these implicit obligations. An LLM extracts a functional-semantic graph from the specification; a symbolic engine then matches it against a CWE pattern ontology to surface mitigation-evidence gaps and signal-level obligations; the LLM finally revises RTL under those obligations in a functionality-preserving two-stage generation. Across five models and four languages, RTL-Obliger raises mean all-pass from 49.6-51.4% (SecV/RESCUE) to 61.6%, with higher security and functional rates than these secure-generation baselines.

cs.CR↗

arXiv2026

Answer Is Cheap, Show Me the Evidence! Augmenting Automated Vulnerability Assessment with Evidence

Software vulnerability (SV) assessment helps prioritize remediation by characterizing reported vulnerabilities. Existing automated methods predict assessment results from SV reports (SVRs), but often overlook information in rich text, such as screenshots and code snippets, as well as contextual information about vulnerable projects. They also focus on prediction accuracy without providing explanations or supporting evidence, limiting their practical use when analysts must validate imperfect predictions. We propose EAVA, a framework that uses large language models (LLMs) to assess SVs and provide supporting evidence. EAVA employs specialized LLM agents to process rich-text content and project information, and builds a dedicated assessment model through a two-stage training pipeline. It first uses supervised instruction tuning on automatically annotated reasoning trajectories to inject domain knowledge, and then applies reinforcement learning to improve intrinsic reasoning. EAVA also retrieves similar historical vulnerabilities as supplementary evidence. Experiments on a newly collected SVR dataset show that EAVA outperforms the strongest baseline by 5.3 to 35.2 percent across multiple metrics. Ablation studies confirm the effectiveness of assessment-specific model training and information enrichment. A user study with security experts further demonstrates that the evidence provided by EAVA is useful and practical for real-world SV assessment.

cs.SE↗

arXiv2026

Execution-Anchored Hallucination Calibration Reranking for Verilog Code Generation

Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, yet their performance degrades significantly on low-resource Hardware Description Languages such as Verilog. While multi-candidate sampling improves the likelihood of generating correct solutions, au-tomatically selecting the optimal candidate remains an open challenge. Through a systematic empirical study across nine models and two benchmarks, we identify two critical limitations:(1) existing execution-based reranking methods, which rely on testbench pass/fail outcomes, exhibit poor domain transferability due to low-quality generated testbenches; and (2) LLM-as-a-Judge suffers from reasoning hallucination, producing incon-sistent judgments for execution-equivalent code. These findings reveal two signal types with orthogonal errors: execution signals(deterministic but testbench coverage limited)and reasoning signals (semantically rich but hallucination-prone). Their orthog-onality suggests combining the two signals, yet in our experiments letting the reasoner directly observe execution results merely anchors its judgments on test outcomes; we therefore acquire the two signals independently and fuse them only at the decision stage. Based on these insights, we propose EAHC, an Execution-Anchored Hallucination Calibration reranking framework that anchors reasoning judgments to execution behavior so that execution-equivalent candidates receive consistent scores, which implements a dual-channel architecture: EAHC-R, a 4B reasoning discriminator; and EAHC-T, a testbench generator leveraging RAG for execution verification.

cs.SE↗

arXiv2026

RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

In modern AI frameworks, GPU kernels are key to overall system performance. Combining usability, portability, and near-handwritten CUDA performance, Triton is widely adopted for implementing GPU kernels. Recent advances show the potential of large language models (LLMs) to automatically generate Triton kernels, reducing the manual effort required from expert kernel developers. Several benchmarks evaluate LLM-generated Triton kernels. However, they suffer from three key limitations: (1) they restrict tasks to PyTorch-to-Triton translation, failing to reflect the diversity and complexity of real-world Triton tasks; (2) they evaluate only individual-kernel performance rather than end-to-end performance, the core criterion for real-world deployment in AI frameworks; and (3) they rely on manually written evaluation scripts for individual kernels, which may contain flaws that models can exploit to bypass correctness checks and obtain inflated scores. To address these limitations, we introduce RealisticTritonBench, the first benchmark to derive Triton kernel generation tasks from real-world pull requests in popular AI frameworks, enabling realistic, production-like evaluation. RealisticTritonBench systematically extracts PRs that modify Triton kernels from popular open-source AI frameworks and transforms them into generation tasks with concrete engineering contexts. Each task takes a natural language requirement as input and requires a corresponding Triton kernel implementation, with a complete and reproducible evaluation environment. Unlike prior benchmarks focused on isolated kernel performance, RealisticTritonBench integrates generated kernels into their original frameworks and evaluates them using end-to-end tests, enabling a more faithful assessment. We evaluate leading LLMs on RealisticTritonBench and find that they still struggle with real-world Triton kernel generation tasks.

cs.SE↗

arXiv2026

SmellCC: A Tool for Automated Code Smells Remediation

Code smells significantly threaten software maintainability by accumulating technical debt, yet developers often lack the resources to manually address these flaws under tight release schedules. While static analysis tools like SonarQube provide precise detection, they function largely as passive alert systems, leaving the burden of refactoring on developers. To bridge this gap, we present a novel cleaning tool, namely SmellCC, a Visual Studio Code extension that augments SonarQube with an LLM-based pipeline to automatically detect and refactor Python code smells. By employing Chain-of-Thought (CoT) and few-shot learning, SmellCC provides in-place, one-click remediation for the top-10 most frequent smells, effectively preventing the accumulation of technical debt during development. Our quantitative evaluation demonstrates that our SmellCC is promising in helping developers effectively eliminate code smells (96.8\% cleaning rate) with high accuracy (i.e., 91.3\%), ensuring that the refactored code remains syntactically correct and behavior-preserving, thereby significantly improving long-term software maintainability.

cs.SE↗

arXiv2026

AgentExecutor: Partial Code Execution via Agentic Context Generation

Executing code snippets is essential for dynamic program analysis, but it remains challenging to execute an arbitrary code snippet due to issues like missing context and incomplete dependencies. Existing approaches to partial code execution, such as LExecutor and Treefix, leverage the power of language models to infer missing information and enable execution. However, they suffer from (i) limited action spaces and feedback, and (ii) rigid optimization strategies, which restrict their effectiveness and efficiency. In this paper, we propose AgentExecutor, a novel multi-agent framework for partial code execution. Our approach introduces a three-phase design: execution environment preparation, dynamic exploration with iterative refinement, and prefix evolution via program synthesis. Supported by the power of LLM agents who can think, act, and get feedback iteratively, AgentExecutor is able to autonomously explore a richer action space, enabling diverse operations such as creating resource files and resolving environment configuration. Furthermore, it adopts adaptive optimization strategies, including coverage-guided context pruning and prefix evolution via program synthesis, to systematically improve the execution quality of partial code. We evaluate AgentExecutor on two widely used datasets comprising Stack Overflow snippets and open-source project code. The results show that AgentExecutor achieves up to 94% and 90% code coverage, outperforming the state-of-the-art approach Treefix by 19.9% and 13.8%, respectively. In addition, AgentExecutor significantly reduces execution time (by up to 80.3%) and cost (by up to 56.6%). These findings demonstrate that AgentExecutor provides an effective and efficient solution for partial code execution.

cs.SE↗

arXiv2026

Automating Just-In-Time Python Type Annotation Updating

Type annotations are more and more popular in Python projects to avoid type errors caused by Python's dynamic typing feature. However, when developers change source code, these type annotations are often neglected or overlooked, resulting in outdated and inconsistent type annotations. Such obsolete type annotations can hinder program comprehension, mislead developers, and even introduce bugs in the future. Therefore, it is necessary to avoid and correct these inconsistent type annotations from the very beginning. In this work, we argue that obsolete type annotations can be reduced and even avoided by automatically updating type annotations alongside code changes. We refer to this task as "Just-In-Time (JIT) type annotation updating". To solve this task, we propose a novel LLM-based approach named TypeUp (Type Annotation Updator) to automate this task. TypeUp can automatically generate new type annotations based on the old type annotations and corresponding code changes. Specifically, TypeUp guides LLM to perform type annotation updates by eliciting its knowledge and logical reasoning power and learning from similar code changes. The evaluation results show that TypeUp outperforms state-of-the-art type infer approach (i.e., TypeGen) by 41.9% on our task. Moreover, we conducted an in-the-wild evaluation with real-world software projects, 20 out of 25 type annotation updates generated by our approach have already been confirmed by developers, showing our approach's practical value in real-world environments.

cs.SE↗

arXiv2026

WinTA-GIL: Windowed Trajectory Alignment for GNSS-IMU-LiDAR Heading Refinement in Intermittent Signal Environments

Although multi-source fusion positioning systems have achieved significant progress, accurate and reliable heading estimation remains a critical challenge due to the lack of gravitational constraints and the inherent weak observability of heading in complex environments. Most existing methodologies are specifically tailored for the startup phase, relying on a singular initial alignment to establish the heading reference. Consequently, these approaches lack the adaptability required to refine heading estimates dynamically, which renders the system highly vulnerable to accumulated drift and observation noise during prolonged navigation or immediately following GNSS signal outages. To address these limitations, this paper proposes WinTA-GIL, a novel heading refinement framework that integrates information from Global Navigation Satellite System (GNSS), Inertial Measurement Unit (IMU), and Light Detection and Ranging (LiDAR) through a temporal window-based optimization strategy. Unlike conventional alignment methods restricted to the startup phase, WinTA-GIL leverages high-precision local trajectories from LiDAR-Inertial Odometry (LIO) to register against filtered GNSS observations. This approach transforms heading estimation into a repeatable, trajectory-based consistency optimization problem. In particular, an adaptive re-estimation mechanism based on state discrimination is incorporated to trigger heading corrections whenever necessary, thereby effectively suppressing the inertial drift accumulated during challenging conditions. Extensive experiments on both open-source and self-collected datasets demonstrate that WinTA-GIL significantly outperforms state-of-the-art approaches in both estimation accuracy and system robustness.

cs.RO↗

arXiv2026

Refploit: Facilitating Exploit Construction via Code-Agent Trajectory Repair

Vulnerability exploits play a crucial role in assessing the downstream impact of Java library vulnerabilities. While some vulnerabilities are accompanied by disclosed exploit references, automatically reproducing such references into runnable exploits remains challenging because they are often incomplete, unstructured, or only describe partial reproduction steps. Recent code agents provide a promising way to automate this process, but our study shows that their generated exploits often appear successful without triggering the actual vulnerable logic, such as replacing vulnerable APIs with self-implemented functions. To address this, we propose Refploit, an LLM-based trajectory recovery framework for facilitating vulnerability reproduction from public exploit references. The key insight is that a failed agent trajectory is not entirely useless. It may have already completed some reproduction subtasks while also revealing misleading directions that should be avoided. Refploit first validates an agent-generated exploit through differential execution. When the exploit is ineffective, Refploit analyzes its reproduction progress, locates the trajectory segments associated with the reproduction progress, and derives constraints to guide focused recovery. We evaluate Refploit on three open-source Java vulnerability datasets, covering 172 exploit references for 143 vulnerabilities. Under DeepSeek-V4-Flash, Refploit successfully reproduces 138 exploits, achieving a reproduction rate of 80.2%. It achieves a 64.3% relative improvement over the initially generated trajectories and outperforms both the SOTA exploit-generation method PoCGen and advanced code agents such as Codex with GPT-5.4. We further adapt Refploit to another code agent and observe consistent improvements, demonstrating its generality.

cs.SE↗

arXiv2026

Mitigating Package Hallucinations in Large Language Models via Model Editing

Large language models (LLMs) have demonstrated strong capabilities in software engineering tasks, such as code generation, library recommendation, and dependency configuration. However, recent studies show that LLMs may suffer from package hallucination, where they generate non-existent or invalid package names. These hallucinations can be exploited in software supply chain attacks, as attackers may register malicious packages under hallucinated names. Therefore, mitigating package hallucination is important for improving the reliability and security of LLM-assisted software development. In this paper, we introduce BOUND, a lightweight localized model editing framework for mitigating package hallucinations in LLMs. BOUND formulates package hallucination mitigation as a package-validity boundary editing problem, where the boundary refers to the model's ability to distinguish valid packages from hallucinated package names under a given task context. It first locates modules related to package hallucination through a risk-aware localization strategy, and then edits these modules with lightweight LoRA adapters using a boundary-aware objective that reinforces valid packages, suppresses hallucinated packages, and preserves locality behavior. Experimental results show that BOUND effectively reduces package hallucinations while preserving valid package recommendations. In the package recommendation task, BOUND reduces package-level hallucination rate (Package-HR) by 79.9% on edit prompts and by 65.4% on unseen prompts. The learned package-validity boundary further generalizes to other package-related tasks, reducing Package-HR by 12.8% in code generation and by 34.0% in pip install recommendation. These results show that BOUND refines the package-validity boundary of LLMs and improves the reliability of package-related outputs.

cs.SE↗

arXiv2026

Morphing into Hybrid Attention Models

Hybrid attention models improve long-context efficiency by retaining only a subset of full-attention layers and replacing the remaining layers with linear attention. However, the effectiveness of Transformer-to-hybrid conversion critically depends on which layers preserve full attention. Existing hybrid layer selection methods typically rely on heuristic strategies such as fixed placement patterns or layerwise scoring, implicitly treating layer importance as isolated and overlooking the interdependent layer effect under a global hybrid configuration. In this work, we formulate hybrid layer selection as a budget-constrained subset optimization problem. We further propose FlashMorph (Fast LAyer Selection for Hybrid MORPHing), an effective, efficient and scalable layer selection method for Transformer-to-hybrid conversion. FlashMorph first constructs a morphable model by equipping each full-attention layer with a converted linear-attention branch. It then freezes all model weights and jointly optimizes layerwise gates on synthetic long-context retrieval data, with a linearization regularization that encourages the model to rely on linear attention for efficiency. The learned gates are discretized under a preset full-attention budget to instantiate the hybrid architecture, followed by standard logits distillation and long-context finetuning. Extensive experiments show that FlashMorph discovers more effective hybrid configurations, preserves strong long-context recall and general benchmark performance while substantially reducing layer selection cost compared with existing layer selection methods, demonstrating its effectiveness, efficiency, and scalability.

cs.CL↗

arXiv2026

IntentTester: Intent-Driven Multi-agent Framework for Cross-Library Test Migration

Unit tests capture both functional checks and domain-specific knowledge, but this knowledge remains locked within individual projects and is rarely reused across libraries with overlapping functionality. Existing migration techniques based on structural code mappings (e.g., API signatures) often break down under divergent designs or cross-language settings, resulting in non-executable migrated tests. In this paper, we present IntentTester, a multi-agent framework for intent-driven test reuse. Instead of translating raw code, IntentTester abstracts tests into a language-agnostic Test Description Language (TDL), aligns them with semantically related entities and dependencies in a repository graph, and synthesizes executable tests through LLM-guided reasoning and iterative validation. This design enables cross-library and cross-language migration without manual intervention, producing migrated tests that existing structure-mapping approaches cannot achieve. We evaluate IntentTester on nine open-source projects across three domains (JSON, HTML, and Time) and two languages (Java and Python). IntentTester generates 2,776 syntactically correct tests with 85\% correctness; in comparison, the two baselines achieve 51\% and 43\%. Among them, 2,410 tests executed successfully, yielding a 74\% effectiveness rate. Beyond higher success rates, IntentTester also surfaced previously unknown defects including stack overflows, null dereferences, and parsing inconsistencies, several of which have been acknowledged or patched by maintainers. Our results show that intent-driven migration shifts the focus from code mappings to semantic alignment, allowing practical cross-library and cross-language test reuse while improving test quality and exposing implementation flaws.

cs.SE↗

arXiv2026

ATTAIN: Automated Exploit Failure Analysis through Trace-Driven Diff Analysis

Exploits are widely used to check whether library vulnerabilities appear in different versions and to mark affected version ranges. Exploit-based checks sometimes fail because exploits stop running on many versions after API or environment changes. Commit-based methods, such as SZZ-style analysis, sometimes miss the right introduce commits and spread labels incorrectly along long version chains. These problems leave many affected versions unlabeled or wrongly labeled and make manual exploit failure analysis very expensive and impractical at scale. We present ATTAIN, a trace-driven diff analysis framework with three modules to assess vulnerability presence across evolving library versions. The modules are trace construction, diff exploration, and affected-version judgment. The trace construction module executes an exploit across historical library versions and compares their behaviors to capture cross-version execution divergences. Using these divergences, the diff exploration module guides an LLM through a finite-state tool loop to autonomously search over version changes and collect vulnerability-relevant diff hunks. The affected-version judgment module reasons over the collected evidence to determine whether the vulnerability exists in each version and outputs the affected version range. We evaluate ATTAIN on an extensive dataset comprising 224 CVEs and 25,943 library versions across 128 libraries. ATTAIN achieves an F1-score of 93.24%, outperforming the commit-based methods V-SZZ and LLM4SZZ by 116.28% and 33.30%, respectively. ATTAIN uses short tool-guided prompts and a fixed number of iterations, keeping token usage low. It matches or surpasses existing methods on frequent CWE types, including cases where exploit runs fail for non-vulnerability reasons or commit messages do not clearly delimit affected versions.

cs.SE↗

arXiv2026

On the Shoulders of Giants: Empowering Automated Smart Contract Auditing via the GiAnt Corpus

High-quality smart contract auditing datasets are crucial for evaluating security tools and advancing smart contract security research. Two major limitations of existing datasets are the manual-induced scalability bottleneck and the deficiency in data granularity and diversity. To address these limitations, we propose GiANT, an automated framework designed to curate smart contract auditing datasets by distilling vulnerability insights from real-world auditing reports. GiANT employs a divide-and-conquer strategy coupled with the Chain-of-Thought technique to extract structured vulnerability information from Code4rena reports, followed by an LLM-as-a-judge mechanism to perform rigorous quality assurance. To evaluate GiANT's effectiveness, we run it on 388 real-world audit reports and generate the GiAnt Corpus comprising 7,711 vulnerability findings across five severity levels. Manual assessment of the dataset demonstrates exceptional reliability in information extraction, achieving a mean quality score of $4.76\pm0.37$ (out of 5) with inter-rater agreement $\kappa$ of 0.88. We further validate the practicality of our dataset by benchmarking 4 state-of-the-art LLMs on vulnerability detection, code summarization, mitigation recommendation, and automated gas optimization tasks, to establish performance baselines, thereby providing a valuable data foundation for future research in automated smart contract auditing.

cs.CR↗

arXiv2026

Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization

LLM-based automated scoring approaches near-human performance, but scaling to new tasks remains bottlenecked by the per-item human configuration of upstream stages such as rubric construction. Human experts bypass this bottleneck through evaluation heuristics developed over extensive practice. We ask whether LLMs can learn similar heuristics directly from scoring experience, and formalize this as the concept of assessment skills: item-independent natural-language procedural knowledge that guides LLMs through specific stages of the scoring workflow. Focusing on rubric construction as a first instantiation, we propose an iterative framework that decomposes a skill into a fixed scaffold and learnable item-agnostic rules, refining the rules through LLM-driven diagnosis of scoring errors and validation-gated selection. The framework requires no expert-written rubric. On all ten ASAP-SAS items, optimized skills substantially improve LLM-based scoring and frequently surpass the dataset-provided expert rubric. Cross-item transfer experiments further reveal that learned skills capture both generalizable and item-specific patterns.

cs.CL↗

arXiv2026

Exploiting LLM Agent Supply Chains via Payload-less Skills

Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for systematic security evaluation. Current auditing mechanisms are effective at identifying explicit code payloads and predefined threat contents through security scanning. These detection mechanisms are bypassed if malicious behaviors lack direct injection and are instead synthesized dynamically at runtime through the agent's inherent generative capabilities. Exploring this blind spot, we introduce Semantic Compliance Hijacking (SCH), a payload-less supply chain attack targeting autonomous coding environments. The SCH approach translates malicious goals into unstructured natural language instructions formatted as necessary compliance rules, leading the agent to generate and execute unauthorized code. To assess the real-world viability of this attack, we developed an automated pipeline to evaluate its effectiveness across a test matrix comprising three mainstream agent frameworks and three distinct foundation models using contextualized scenarios. The findings demonstrate the pervasive nature of this threat, with SCH achieving peak success rates of up to 77.67% for confidentiality breaches and 67.33% for Remote Code Execution (RCE) under the most vulnerable configurations. Furthermore, the introduction of Multi-Skill Automated Optimization (MS-AO) further boosted attack efficacy. By omitting recognizable Abstract Syntax Tree (AST) signatures and explicit harmful intents, the manipulated skill files maintained a 0.00% detection rate, evading current scanning tools. This research highlights an underexplored attack surface within agent supply chains, pointing to a necessary transition from signature-based detection models toward semantic intent validation.

cs.CR↗

arXiv2026

From Mirage to Grounding: Towards Reliable Multimodal Circuit-to-Verilog Code Generation

Multimodal large language models (MLLMs) are increasingly used to translate visual artifacts into code, from UI mockups into HTML to scientific plots into Python scripts. A circuit diagram can be viewed as a visual domain-specific language for hardware: it encodes timing, topology, and bit level semantics that are invisible to casual inspection yet safety critical once fabricated in silicon. Translating such diagrams into register-transfer-level(RTL) code therefore represents an extreme reliability test for vision-to-code generation. We reveal a phenomenon we call Mirage: replacing a circuit diagram with a blank image leaves Pass@k unchanged or even higher, because models bypass the visual input and instead exploit identifier semantics in the module header to retrieve canonical RTL templates. This constitutes a new, highly covert class of defect in AI-assisted code generation that directly undermines MLLMs' trustworthiness. To quantify the effect, we construct C2VEVAL and evaluate eight MLLMs under a paired Normal/Anony protocol in which Anony mode anonymizes all identifiers in both the diagram and the module header; Anony-mode scores drop sharply across all models, confirming that high Normal-mode accuracy is largely a Mirage. We then propose VeriGround (4B), trained with identifier anonymization, refusal augmentation, and D-ORPO (Decision-Focused ORPO) preference alignment that up-weights pivotal generate-or-refuse tokens. VeriGround achieves Functional Pass@1 of 46.11%/42.51%(Normal/Anony) with a False Refusal Rate of only 1.20%/0.00%, while maintaining >92% Refusal Rate on blank images. With only 4B parameters, VeriGround performs on par with GPT-5.4 under Normal and significantly outperforms all baselines under Anony, confirming genuine visual grounding.

cs.SE↗

arXiv2026

An Empirical Study of Speculative Decoding on Software Engineering Tasks

Large Language Models (LLMs) have become widely used for Software Engineering (SE) tasks, spanning from function-level code generation to complex repository-level workflows. However, the high latency of autoregressive inference remains a significant bottleneck, hindering their deployment in interactive environments. While Speculative Decoding (SD) offers a promising technique for lossless acceleration, prior research on long-context repository-level tasks and complex agentic interactions remains limited. To bridge this gap, we present the first systematic empirical study to evaluate the effectiveness of SD in SE tasks. We systematically benchmark a comprehensive spectrum of strategies, encompassing both model-based and model-free methods, across representative generation, editing, and repair scenarios. Our empirical results indicate that SD demonstrates clear potential for accelerating inference, particularly for smaller models that achieve higher speedups than those of their larger counterparts. We find that the effectiveness of SD methods varies across different task scenarios. Model-based approaches are well-suited for code generation, whereas model-free methods are better adapted to repository-level repair and editing scenarios. Furthermore, we observe that the repetitiveness of SE tasks improves the performance of model-free methods. In contrast to natural language tasks, the higher predictability of SE tasks allows for more aggressive hyperparameters. Our findings are summarized as guidelines to help increase inference efficiency for SE scenarios.

cs.SE↗