arXiv subjects

Jie JW Wu

Publications and source records attributed to Jie JW Wu.

13 recordsLinked to original sources

arXiv2026

Verification as an Architectural Layer for LLM Agents: A V-Model Design, and a Pilot Study of Its Deterministic Core

Large language model (LLM) agents built on the ReAct pattern concentrate four responsibilities in one model: selecting a strategy, choosing each action, formatting it, and judging whether the result is adequate. Nothing outside the generative loop can reject its output, so an agent that cannot make progress does not report failure; it runs until an external budget stops it. We propose treating verification as an architectural layer by adapting the V-model from software engineering: specification levels descend from requirements to individual steps, each level is paired with a dedicated verifier, a deterministic controller enforces every verdict, and only verification outcomes write to memory, so a rejection localizes the level that introduced the fault and an agent halts by declining rather than by exhaustion. Each verifier separates a zero-cost deterministic \emph{gate} from an optional LLM \emph{judge}, so the contribution and cost of each can be measured independently. We report a pilot implementing the acceptance- and unit-level verifier pairs, comparing five configurations that share one executor, tool set, and scorer and differ only in verification, on the four-hop stratum of MuSiQue with an 8B-parameter backbone. Across 47 executions, the two unverified configurations answered none of ten questions, every run ending at a step cap or provider token limit; the verified configuration without a planner answered eight and abstained on the rest. Deterministic gates produced eight of the nine observed corrections at zero marginal cost, and planning degraded performance once verification was present. These results characterize termination behavior, not accuracy at scale; we outline a twelve-month plan to complete and evaluate the full architecture, including the integration-level pair the pilot omits.

cs.SE↗

arXiv2026

Metamorphic Testing for Clinical ML Models: A Framework Proposal and Pilot Study

Machine learning models for clinical prediction tasks, such as in-hospital mortality and sepsis onset, routinely achieve high AUROC scores. However, AUROC measures ranking performance rather than clinical sensibility. A model may rank patients correctly overall while predicting a lower mortality risk when a patient's SOFA score worsens, contradicting established medical knowledge. This paper proposes applying metamorphic testing (MT) to clinical machine learning models to evaluate behavioral correctness without requiring ground-truth labels for individual predictions. We design a catalog of 12 candidate metamorphic relations (MRs) for three ICU prediction tasks using the MIMIC-III and MIMIC-IV datasets, with each MR grounded in an authoritative clinical guideline. We further propose a five-layer validation strategy to ensure that MRs are clinically sound before deployment. As a feasibility study, we evaluate the approach on the UCI Heart Disease dataset. Although the three clinical models achieve strong predictive performance (AUROC = 0.849-0.900), they exhibit MT violation rates ranging from 27% to 87% across five pilot MRs. An injected-fault experiment further shows that a sign-negation error in a blood pressure feature remains undetected by AUROC but increases the MT violation rate by 31-67 percentage points. These findings suggest that metamorphic testing provides a valuable complement to conventional performance metrics for assessing the behavioral correctness of clinical prediction models.

cs.SE↗

arXiv2026

GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents

With data-driven development now widely adopted, online A/B testing is an established method for measuring the effects of new technologies. However, deploying online experiments demands resources for design, implementation, and deployment, and may negatively impact users (e.g., unsafe or unethical outcomes) while requiring weeks of data collection. To address this, the growing research area of off-policy evaluation (OPE), or offline A/B testing, assesses new technologies offline using previously collected logged data. OPE is also a fundamental problem in reinforcement learning and is important where online testing is expensive or risky, such as healthcare, recommender systems, education, and robotics. Despite advances in code-generation large language models (LLMs) and agentic workflows, little is known about whether and how LLMs and LLM-based agents can automatically optimize OPE implementations. We propose GrowthHacker, a benchmark that evaluates baseline LLMs and LLM-based agents on large-scale public datasets. GrowthHacker autonomously and iteratively modifies code, runs OPE, and uses the metrics to guide subsequent optimization. We evaluate methods on Open Bandit Pipeline (OBP) and Scope-RL, and develop a two_agent framework that addresses limitations of existing frameworks while reducing complexity. Across both libraries, two_agent shows the highest reliability (98.1%-100% success rate) and positive-outcome rate (78%), with a median improvement of 4.4% among positive outcomes; CrewAI achieves the highest average improvement (37.9%) and is the only framework with zero extreme-value failures. AutoGen and Default each reach 65% positive-outcome rates. These results establish the feasibility of using LLM-based agents as automated "growth hackers" to continuously improve OPE systems, with implications for scaling data-driven decision-making where manual optimization is expensive.

cs.SE↗

arXiv2025

MANTRA: a Framework for Multi-stage Adaptive Noise TReAtment During Training

The reliable application of deep learning models to software engineering tasks hinges on high-quality training data. Yet, large-scale repositories inevitably introduce noisy or mislabeled examples that degrade both accuracy and robustness. While Noise Label Learning (NLL) has been extensively studied in other fields, there are a few works that investigate NLL in Software Engineering (SE) and Large Language Models (LLMs) for SE tasks. In this work, we propose MANTRA, a Multi-stage Adaptive Noise TReAtment framework that embeds noise diagnosis and mitigation directly into the fine-tuning process of code-Pretrained Language Models (PTM) and code-LLMs. We first investigate the effect of noise at varying levels on convergence and loss trajectories of the models. Then we apply an adaptive dropout strategy guided by per-sample loss dynamics and Gaussian Mixture Model clustering to exclude persistently noisy points while preserving clean data. Applying to code summarization and commit intent classification, our experiments reveal that some LLMs are more sensitive to noise than others. However, with MANTRA, the performance of all models in both tasks is improved. MANTRA enables researchers and practitioners to reduce the impact of errors introduced by the dataset in training, saves time in data cleaning and processing, while maximizing the effect of fine-tuning.

cs.SE↗

arXiv2025

FISCAL: Financial Synthetic Claim-document Augmented Learning for Efficient Fact-Checking

Financial applications of large language models (LLMs) require factual reliability and computational efficiency, yet current systems often hallucinate details and depend on prohibitively large models. We propose FISCAL (Financial Synthetic Claim-Document Augmented Learning), a modular framework for generating synthetic data tailored to financial fact-checking. Using FISCAL, we generate a dataset called FISCAL-data and use it to train MiniCheck-FISCAL, a lightweight verifier for numerical financial claims. MiniCheck-FISCAL outperforms its baseline, surpasses GPT-3.5 Turbo and other open-source peers of similar size, and approaches the accuracy of much larger systems (20x), such as Mixtral-8x22B and Command R+. On external datasets FinDVer and Fin-Fact, it rivals GPT-4o and Claude-3.5 while outperforming Gemini-1.5 Flash. These results show that domain-specific synthetic data, combined with efficient fine-tuning, enables compact models to achieve state-of-the-art accuracy, robustness, and scalability for practical financial AI. The dataset and scripts are available in the project repository (link provided in the paper).

cs.AI↗

arXiv2025

A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages

Large Language Models (LLMs) have shown impressive capabilities in code generation for popular programming languages. However, their performance on Low-Resource Programming Languages (LRPLs) and Domain-Specific Languages (DSLs) remains a significant challenge, affecting millions of developers-3.5 million users in Rust alone-who cannot fully utilize LLM capabilities. LRPLs and DSLs encounter unique obstacles, including data scarcity and, for DSLs, specialized syntax that is poorly represented in general-purpose datasets. Addressing these challenges is crucial, as LRPLs and DSLs enhance development efficiency in specialized domains, such as finance and science. While several surveys discuss LLMs in software engineering, none focus specifically on the challenges and opportunities associated with LRPLs and DSLs. Our survey fills this gap by systematically reviewing the current state, methodologies, and challenges in leveraging LLMs for code generation in these languages. We filtered 111 papers from over 27,000 published studies between 2020 and 2024 to evaluate the capabilities and limitations of LLMs in LRPLs and DSLs. We report the LLMs used, benchmarks, and metrics for evaluation, strategies for enhancing performance, and methods for dataset collection and curation. We identified four main evaluation techniques and several metrics for assessing code generation in LRPLs and DSLs. Our analysis categorizes improvement methods into six groups and summarizes novel architectures proposed by researchers. Despite various techniques and metrics, a standard approach and benchmark dataset for evaluating code generation in LRPLs and DSLs are lacking. This survey serves as a resource for researchers and practitioners at the intersection of LLMs, software engineering, and specialized programming languages, laying the groundwork for future advancements in code generation for LRPLs and DSLs.

cs.SE↗

arXiv2025

Can Code Language Models Learn Clarification-Seeking Behaviors?

Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, a gap remains between their output and the problem-solving strategies of human developers. Unlike humans, who spend substantial time disambiguating requirements through iterative dialogue, LLMs often generate code despite ambiguities in natural language requirements, leading to unreliable solutions. Different from prior work, we study whether a Code LLM can be fine-tuned to learn clarification-seeking behavior. While recent work has focused on LLM-based agents for iterative code generation, we argue that the ability to recognize and query ambiguous requirements should be intrinsic to the models themselves, especially in agentic AI where models and humans collaborate. We present ClarifyCoder, a framework with synthetic data generation and instruction-tuning that fine-tunes an LLM to identify ambiguities and request clarification before code generation. Our approach has two components: (1) a data synthesis technique that augments programming datasets with scenarios requiring clarification to generate clarification-aware training data, and (2) a fine-tuning strategy that teaches models to prioritize seeking clarification over immediate code generation when faced with incomplete or ambiguous requirements. We also provide an empirical analysis of integrating ClarifyCoder with standard fine-tuning for joint optimization of clarification-awareness and coding ability. Experimental results show that ClarifyCoder achieves a 63% communication rate (40% absolute increase) and a 52% good question rate (30% absolute increase) on ambiguous tasks, significantly improving LLMs' communication capabilities while maintaining code generation performance.

cs.SE↗

arXiv2025

MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair

Large Language Models (LLMs) have shown high capabilities in several software development-related tasks such as program repair, documentation, code refactoring, debugging, and testing. However, training these models requires massive amount of data and significant computational resources. Adapters are specialized, small modules designed for parameter efficient fine-tuning of LLMs for specific tasks, domains, or applications without requiring extensive retraining of the entire model. These adapters offer a more efficient way to customize LLMs for particular needs, leveraging the pre-existing capabilities of the large model. Model (and adapter) merging have emerged as a technique to develop one model capable of multiple tasks, with minimal or no training required. Although model and adapter merging has shown promising performance in domains such as natural language processing and computer vision, its applicability to software engineering tasks remains underexplored. In this paper, we investigate the effectiveness of merged adapters within the context of software engineering, with a particular focus on the Automated Program Repair (APR) task, through our approach, MergeRepair. In particular, we merge multiple task-specific adapters using three different merging methods, including weight-averaging, ties, and dare-ties, and evaluate the performance of the merged adapter on the APR task. We introduce a continual merging approach, a novel method in which we sequentially merge the task-specific adapters where the order and weight of the merged adapters play a significant role. We further compare the performance of our approach with a baseline method consisting of equal-weight merging applied on parameters of different adapters, where all adapters are of equal importance.

cs.SE↗

arXiv2025

HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent

Large language models (LLMs) have significantly improved their ability to perform tasks in the field of code generation. However, there is still a gap between LLMs being capable coders and being top-tier software engineers. Based on the observation that top-level software engineers often ask clarifying questions to reduce ambiguity in both requirements and coding solutions, we argue that the same should be applied to LLMs for code generation tasks. In this work, we conducted an empirical study on the benchmark and analysis of the communication skills of LLMs for code generation. We define communication skills of LLMs as ``being able to ask clarifying questions when the description of the code generation problem has issues''. We created a new benchmark, HumanEvalComm, by modifying problem descriptions according to three issues: inconsistency, ambiguity, incompleteness. We defined new evaluation metrics such as Communication Rate and Good Question Rate, and then experimented on HumanEvalComm with different Code LLMs, and a new LLM agent approach, Okanagan, to identify and ask questions in ambiguous parts from code and descriptions for further refining the generated code. Finally, we discussed evaluation results by comparing Code LLMs and Okanagan with our findings.

cs.SE↗

arXiv2024

AutoOffAB: Toward Automated Offline A/B Testing for Data-Driven Requirement Engineering

Software companies have widely used online A/B testing to evaluate the impact of a new technology by offering it to groups of users and comparing it against the unmodified product. However, running online A/B testing needs not only efforts in design, implementation, and stakeholders' approval to be served in production but also several weeks to collect the data in iterations. To address these issues, a recently emerging topic, called "Offline A/B Testing", is getting increasing attention, intending to conduct the offline evaluation of new technologies by estimating historical logged data. Although this approach is promising due to lower implementation effort, faster turnaround time, and no potential user harm, for it to be effectively prioritized as requirements in practice, several limitations need to be addressed, including its discrepancy with online A/B test results, and lack of systematic updates on varying data and parameters. In response, in this vision paper, I introduce AutoOffAB, an idea to automatically run variants of offline A/B testing against recent logging and update the offline evaluation results, which are used to make decisions on requirements more reliably and systematically.

cs.SE↗

arXiv2024

An Exploratory Study of V-Model in Building ML-Enabled Software: A Systems Engineering Perspective

Machine learning (ML) components are being added to more and more critical and impactful software systems, but the software development process of real-world production systems from prototyped ML models remains challenging with additional complexity and interdisciplinary collaboration challenges. This poses difficulties in using traditional software lifecycle models such as waterfall, spiral, or agile models when building ML-enabled systems. In this research, we apply a Systems Engineering lens to investigate the use of V-Model in addressing the interdisciplinary collaboration challenges when building ML-enabled systems. By interviewing practitioners from software companies, we established a set of 8 propositions for using V-Model to manage interdisciplinary collaborations when building products with ML components. Based on the propositions, we found that despite requiring additional efforts, the characteristics of V-Model align effectively with several collaboration challenges encountered by practitioners when building ML-enabled systems. We recommend future research to investigate new process models, frameworks and tools that leverage the characteristics of V-Model such as the system decomposition, clear system boundary, and consistency of Validation & Verification (V&V) for building ML-enabled systems.

cs.SE↗

arXiv2024

Investigating the Efficacy of Large Language Models for Code Clone Detection

Large Language Models (LLMs) have demonstrated remarkable success in various natural language processing and software engineering tasks, such as code generation. The LLMs are mainly utilized in the prompt-based zero/few-shot paradigm to guide the model in accomplishing the task. GPT-based models are one of the popular ones studied for tasks such as code comment generation or test generation. These tasks are `generative' tasks. However, there is limited research on the usage of LLMs for `non-generative' tasks such as classification using the prompt-based paradigm. In this preliminary exploratory study, we investigated the applicability of LLMs for Code Clone Detection (CCD), a non-generative task. By building a mono-lingual and cross-lingual CCD dataset derived from CodeNet, we first investigated two different prompts using ChatGPT to detect Type-4 code clones in Java-Java and Java-Ruby pairs in a zero-shot setting. We then conducted an analysis to understand the strengths and weaknesses of ChatGPT in CCD. ChatGPT surpasses the baselines in cross-language CCD attaining an F1-score of 0.877 and achieves comparable performance to fully fine-tuned models for mono-lingual CCD, with an F1-score of 0.878. Also, the prompt and the difficulty level of the problems has an impact on the performance of ChatGPT. Finally we provide insights and future directions based on our initial analysis

cs.SE↗

arXiv2024

Large Language Models Should Ask Clarifying Questions to Increase Confidence in Generated Code

Large language models (LLMs) have significantly improved the ability to perform tasks in the field of code generation. However, there is still a gap between LLMs being capable coders and being top-tier software engineers. Based on the observation that toplevel software engineers often ask clarifying questions to reduce ambiguity in both requirements and coding solutions, I argue that the same should be applied to LLMs for code generation tasks. By asking probing questions in various topics before generating the final code, the challenges of programming with LLMs, such as unclear intent specification, lack of computational thinking, and undesired code quality, may be alleviated. This, in turn, increases confidence in the generated code. In this work, I explore how to leverage better communication skills to achieve greater confidence in generated code. I propose a communication-centered process that uses an LLM-generated communicator to identify issues with high ambiguity or low confidence in problem descriptions and generated code. I then ask clarifying questions to obtain responses from users for refining the code.

cs.SE↗