arXiv subjects

Lionel Briand

Publications and source records attributed to Lionel Briand.

At least 19 recordsLinked to original sources

arXiv2026

When Is Graph Structure Worth Its Cost? The Case for Structure Pricing in Retrieval-Augmented Generation

Graph-based retrieval-augmented generation (RAG) can help answer questions that require information from many documents. However, building a graph often requires many language-model calls during ingestion. It is therefore important to ask whether its quality gains justify the additional cost. We present EffiRAG, a graph-based RAG system designed to reduce this cost. It uses the graph to locate relevant passages and generates answers from the original text. This design preserves source information while keeping graph construction and query processing lightweight. We evaluate EffiRAG on UltraDomain, which contains 120 open-ended questions from four domains. Compared with LightRAG-hybrid, EffiRAG produces the preferred answer on 93 questions. LightRAG is preferred on 7, and the remaining 20 are splits. EffiRAG also reduces total system cost by 57 percent, from USD 0.952 to USD 0.408. The cost includes language-model calls during ingestion and querying. The advantage remains as the corpus grows. At 10 and 20 documents per domain, EffiRAG uses a lightweight, non-LLM filter to skip low-salience chunks. It remains preferred over LightRAG-hybrid. It costs 4.2 times and 4.5 times less, respectively. The comparisons identify different quality-cost trade-offs. Graph-based RAG systems should therefore be evaluated by both answer quality and cost. The results favor graph structure that locates and preserves source evidence.

cs.AI↗

arXiv2026

MANGO: Automated Multi-Agent Test Oracle Generation for Vision-Language-Action Models

Vision-Language-Action (VLA) models are emerging robotic control systems that integrate perception, language understanding, and action generation in a unified architecture. Existing testing approaches for VLA-enabled robots rely on manually constructed symbolic test oracles that determine task success from final environment states. These oracles are costly to construct, require domain expertise, and are often tightly coupled to specific tasks and environments, limiting scalability and reuse. Furthermore, they provide only end-state assessments of task outcomes, offering limited insight into intermediate behavior and fault localization. To address these limitations, we introduce MANGO, a multi-agent framework that automatically generates fine-grained oracles from natural-language descriptions of robotic tasks. MANGO first generates a reusable library of atomic tasks, then generates simulator-grounded oracle definitions for each atomic task, and finally produces executable fine-grained oracles by decomposing complex instructions into ordered sequences of atomic actions and corresponding oracles. The framework uses collaborative Generator, Assessor, and Judge agents that iteratively refine generated artifacts through structured feedback. We evaluate MANGO on the LIBERO_10 and RoboCasa Humanoid Tabletop benchmarks. Results show that MANGO generates executable, fine-grained oracles that detect a similar number of failures as symbolic oracles while accurately localizing them and providing richer diagnostic information. Through ablation studies, we further analyzed component contributions and the effect of initial task set, while preserving oracle quality. Overall, the results show the feasibility and effectiveness of test oracle generation for VLA-enabled robots testing.

cs.SE↗

arXiv2026

LLM-Driven Cost-Effective Requirements Change Impact Analysis

Requirements are inherently subject to change throughout the software development lifecycle. Within the limited budget available to requirements engineers, manually identifying the impact of such changes on other requirements is error-prone and effort-intensive, especially in regulated domains. This can lead to overlooked impacted requirements, which, if not properly managed, can cause serious issues in downstream tasks. Inspired by the growing potential of large language models (LLMs) across diverse domains, we propose ProReFiCIA, an LLM-driven approach to automatically identify impacted requirements when changes occur. We conduct an extensive evaluation of ProReFiCIA using several LLMs and prompt variants tailored to this task. Using the best LLM-prompt combination, ProReFiCIA achieves 85.7% recall on an unseen industrial dataset, demonstrating its effectiveness in identifying impacted requirements. Further, the cost of applying ProReFiCIA remains small, as the engineer only needs to review the predicted impacted requirements, which represent 3.0% of the entire set of requirements. Lastly, incorporating domain knowledge via RAG increases recall to 95.8% while slightly raising the cost to 3.4%.

cs.SE↗

arXiv2026

LLM-based Low-Level Integration Test Generation for Java

Large language models (LLMs) show promise for automated test generation, but most approaches target unit tests with mocked dependencies. Low-level integration testing instead exercises a class with its real, in-project dependencies, exposing faults involving object construction, API call sequences, and component interactions. Generating such tests is challenging because LLMs may lack project-specific knowledge (not knowing) or violate provided constraints (not following). We present IntTestGen, an LLM-based approach that combines context-enriched generation with constraint-enforced fixing. It mines dependency usage patterns from project code to guide test generation, then applies symbol-, protocol-, and iteration-level constraints during repair using a ClassIndex, a Markov typestate model, and experience memory. We evaluate IntTestGen against the state-of-the-art LLM-based baseline PANTA and search-based baseline EvoSuite on Defects4J and Deps4J, a new post-cutoff benchmark of recent Java repositories. Across the two benchmarks, IntTestGen improves line coverage by 19.99 and 22.69 percentage points, branch coverage by 24.90 and 15.78 points, and mutation score by 13.67 and 0.17 points, respectively. It also covers 378 and 55 additional lines of dependency code. Ablation results confirm that all major components contribute to performance.

cs.SE↗

arXiv2026

A Highly Efficient Diversity-based Input Selection for DNN Improvement Using VLMs

Maintaining or improving the performance of Deep Neural Networks (DNNs) through fine-tuning requires labeling newly collected inputs, a process that is often costly and time-consuming. To alleviate this problem, input selection approaches have been developed in recent years to identify small, yet highly informative subsets for labeling. Diversity-based selection is one of the most effective approaches for this purpose. However, they are often computationally intensive and lack scalability for large input sets, limiting their practical applicability. To address this challenge, we introduce Concept-Based Diversity (CBD), a novel and highly efficient diversity metric for image inputs that leverages Vision-Language Models (VLMs). Our results show that CBD exhibits a strong correlation with Geometric Diversity (GD), an established diversity metric, while requiring only a fraction of its computation time. Building on this finding, we propose a hybrid input selection approach that combines CBD with Margin, a simple uncertainty metric. We conduct a comprehensive evaluation across a diverse set of DNN models, input sets, selection budgets, and six most effective state-of-the-art selection baselines. The results demonstrate that the CBD-based selection consistently outperforms all baselines at guiding input selection to improve the DNN model. Furthermore, the CBD-based selection approach remains highly efficient, requiring selection times close to those of simple uncertainty-based methods such as Margin, even on larger input sets like ImageNet. These results confirm not only the effectiveness and computational advantage of the CBD-based approach, particularly compared to hybrid baselines, but also its scalability in repetitive and extensive input selection scenarios.

cs.CV↗

arXiv2026

CASPER-Change-Aware Slice Prioritization for Efficient Regression Testing of LLM-based systems

Regression testing for LLM-based systems poses unique challenges because individual regression instances provide limited information about system-level regressions. A failure in a single instance does not necessarily indicate a meaningful regression or provide sufficient information to diagnose affected behaviors. Conversely, detecting regressions based only on overall system performance changes is too coarse-grained, as it does not identify which behaviors are affected. This motivates analyzing regression instances at an intermediate level through test suite slices. To address this challenge, we propose CASPER, a change-aware slice prioritization framework for efficient regression testing of prompt-level and model-level changes in LLM-based systems. CASPER first identifies regression slices containing semantically related instances with consistent performance characteristics using an evolutionary slice identification approach. Given a change to an LLM-based application, CASPER prioritizes slices according to their likelihood of regression using behavioral information extracted from execution logs. We instantiate CASPER in the software issue resolution domain and evaluate slice identification against clustering-based baselines and regressed slice prioritization against a random ranking baseline. Results show that CASPER generates more consistent slices while maintaining comparable or better semantic coherence and improves regressed slice prioritization across different LLM-based system changes and testing budgets.

cs.SE↗

arXiv2026

Retromorphic Testing with Hierarchical Verification for Hallucination Detection in RAG

Large language models can still hallucinate in retrieval-augmented generation (RAG), producing claims that are unsupported by or conflict with the retrieved context. Detecting such errors remains challenging when faithfulness is judged solely against the retrieved context: many existing detectors return holistic answer-level scores, while others target open-domain factuality or fail to provide evidence-grounded diagnostics. We present RT4CHART, a retromorphic testing framework for context-faithfulness assessment. RT4CHART decomposes an answer into independently verifiable claims, performs hierarchical local-to-global verification against the retrieved context, and assigns each claim one of three labels: entailed, contradicted, or baseless. It further maps these claim-level decisions back to specific answer spans and returns explicit context-side evidence, enabling fine-grained auditing rather than opaque scoring. We evaluate RT4CHART on RAGTruth++ (408 samples) and our re-annotated RAGTruth-Enhance (2,675 samples). RT4CHART achieves the best answer-level hallucination-detection F1 score among the evaluated baselines. On RAGTruth++, it attains a precision of 0.845, a recall of 0.718, and an F1 score of 0.776, representing an 83% relative improvement over the strongest baseline. It also achieves a span-level F1 score of 47.5% on RAGTruth-Enhance. Ablation studies show that claim-based local processing drives most of the observed improvement, while global verification provides selective benefits across datasets. Finally, our re-annotation identifies 1.68X more hallucination cases than the original labels, suggesting that commonly used benchmarks substantially underestimate the prevalence of hallucination.

cs.CL↗

arXiv2026

Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents

Conversational LLM agents can cause real-world harm when their internal workflows fail, such as completing a transaction without confirmation. Testing these state-dependent failures is difficult because critical boundaries, such as identity checks and confirmation gates, are hidden behind multi-turn conversational prerequisites, rendering them inaccessible to standard tests. We present AgentEval, a black-box testing framework that discovers and stresses these stateful boundaries. AgentEval interacts with an agent to mine a \emph{conversational workflow graph}, a model of its behavior. Instead of prompting blindly, AgentEval uses this graph's structure to enumerate specific guards and prerequisites as test targets, replaying the conversational path to a boundary before applying a perturbation. AgentEval then executes each test, determining whether it passes or fails using only the conversation turns. We benchmark AgentEval against a privileged, white-box auditor with access to the agent's underlying source code, which AgentEval never sees. On four $τ^3$-bench agents, AgentEval successfully generates tests covering $23$--$38$ distinct boundaries per agent; ablation studies attribute the gain to the graph's structure: $23$ distinct boundaries versus $12$ with a prompt-only baseline, at lower duplicate and false-alarm rates.

cs.SE↗

arXiv2026

EvoEye: Self-Evolving Runtime Monitoring for Autonomous Driving Systems

Runtime monitoring is essential for detecting impending hazards in autonomous driving systems (ADSs). However, existing ADS runtime monitors have fixed detection capabilities: rule-based monitors cover only manually specified hazards, while learning-based monitors depend heavily on their initial training data and may retain substantial prediction errors. We therefore propose EvoEye, which identifies the current monitor's errors, generates informative executions accordingly, and updates the monitor through self-evolution. To enable effective self-evolution, EvoEye combines a capable runtime monitor with targeted scenario acquisition. FusionMonitor learns cross-module temporal interactions for collision prediction, while BlindSpotEvolver converts current prediction errors into search guidance and uses density-aware mutation to acquire informative executions for subsequent monitor updates. We evaluate EvoEye on Baidu Apollo with CARLA in representative highway and urban scenarios. FusionMonitor improves frame-level Recall by up to 37.8 percentage points at a false positive rate of 0.05, with 2.49 ms latency and 2.8-4.2 seconds of median warning time. Under the same budget, BlindSpotEvolver outperforms uniform and violation-oriented sampling by up to 13.2 F1 points on previously missed unsafe contexts.

cs.SE↗

arXiv2026

BeSpec: Behavior-Level Specification Alignment for Code Generation

LLMs have made substantial progress on automated code generation from natural-language descriptions of desired behavior (intent). Most existing methods improve generated programs through execution-guided code refinement: they generate a candidate solution, execute it, and patch the implementation using feedback, while leaving the underlying specification unchanged. This workflow implicitly assumes that the LLM's understanding of the intent is already correct and complete. In practice, however, intents are often ambiguous or underspecified. As a result, even a capable model may produce a correct implementation of the wrong intent, making specification mismatch a central bottleneck. This paper presents BeSpec, a behavioral model-based approach to specification alignment. BeSpec treats the task description as partial evidence about the intended behavior of the correct program. It first builds an explicit behavioral model, which are checkable properties that valid outputs must satisfy. BeSpec then generates candidate programs, executes them on probe inputs, and compares their observed behavior with the predicted behaviors. When observed behavior does not match the predicted behaviors, BeSpec either refines the specification or rejects the candidate program. We evaluate BeSpec with three LLMs on four benchmarks: CodeContests, xCodeEval, APPS, and the contamination-free LiveCodeBench. Against nine baselines, BeSpec achieves the highest Pass@1 and average pass rate across all settings, improving average Pass@1 over the strongest baseline by 8.1%--25.3% relative across the three LLMs. A failure analysis shows that after alignment, most remaining errors stem from algorithmic difficulty rather than misunderstood specifications, while ablation studies confirm that each major component of BeSpec contributes positively.

cs.SE↗

arXiv2026

Cleaning Logs for Downstream Tasks (Registered Report)

Background: Software systems generate logs during execution to record critical events and runtime information for troubleshooting and monitoring. However, in practice, logs often contain significant amounts of redundant and irrelevant information, which can negatively impact the performance of downstream analysis tasks, such as model inference and anomaly detection. Objective: The objective of this study is to clean log data by identifying and removing free-standing messages -- messages that are not relevant to the execution behaviors of interest and are interleaved with messages capturing the system's functional behavior. Method: To address this objective, we propose LogPurifier, a task-agnostic log-cleaning approach based on dependency relationships between log message templates. The paper presents a plan for an empirical evaluation using a controlled experimental design to assess the impact of LogPurifier on the effectiveness and efficiency of two downstream tasks: model inference and anomaly detection.

cs.SE↗

arXiv2026

Beyond Strict Rules: Assessing the Effectiveness of Large Language Models for Code Smell Detection

Code smells are symptoms of potential code quality problems that may affect software maintainability, thus increasing development costs and impacting software reliability. Large language models (LLMs) have shown remarkable capabilities for supporting various software engineering activities, but their use for detecting code smells remains underexplored. However, unlike the rigid rules of static analysis tools, LLMs can support flexible and adaptable detection strategies tailored to the unique properties of code smells. This paper evaluates the effectiveness of four LLMs -- DeepSeek-R1, GPT-5 mini, Llama-3.3, and Qwen2.5-Code -- for detecting nine code smells across 30 Java projects. For the empirical evaluation, we created a ground-truth dataset by asking 76 developers to manually inspect 268 code-smell candidates. Our results indicate that LLMs perform strongly for structurally straightforward smells, such as Large Class and Long Method. However, we also observed that different LLMs and tools fare better for distinct code smells. We then propose and evaluate a detection strategy that combines LLMs and static analysis tools. The proposed strategy outperforms LLMs and tools in five out of nine code smells in terms of F1-Score. However, it also generates more false positives for complex smells. Therefore, we conclude that the optimal strategy depends on whether Recall or Precision is the main priority for code smell detection.

cs.SE↗

arXiv2026

CAFD: Concept-Aware DNN Fault Detection using VLMs

Fault detection for Deep Neural Networks (DNNs) has received increasing attention in recent years. While more advanced hybrid approaches have been proposed to combine multiple sources of information and outperform earlier techniques, they often incur substantial computational overhead, limiting scalability and practicality in real-world settings. In this paper, we introduce Concept-Aware Fault Detection (CAFD), a learning-based approach that achieves superior fault detection performance by effectively integrating multiple information sources while maintaining practical efficiency. Specifically, CAFD is trained using a carefully selected set of informative features, including model-based signals derived from the DNN's outputs, distance-based features, and a novel concept-based feature, called Concept Failure Ratio (CFR). CFR leverages Vision-Language Models (VLMs) to extract textual concepts from images and quantify the likelihood that their presence is associated with DNN failures. By incorporating this feature, CAFD benefits from complementary semantic information, enabling more effective fault detection. Our results demonstrate that CFR serves as an effective indicator for DNN fault detection. We conduct an extensive empirical evaluation of CAFD, comparing it against five state-of-the-art baselines across three subject DNN models and datasets, including ImageNet. Across a wide range of constrained selection budgets, CAFD consistently outperforms all baselines in Fault Detection Rate (FDR), achieving average FDR improvements of 18.3% across all investigated subjects and budget sizes.

cs.LG↗

arXiv2026

Supporting System Testing with a Multi-Agent LLM-based Framework for Knowledge Graph Extraction: A Case Study with Ethernet Switch Systems

Technical documents contain rich domain knowledge for automating downstream tasks such as system testing. While this paper focuses on Ethernet switch configuration manuals (ESCMs), we propose a general framework that can be adapted to different industrial contexts. ESCMs provide valuable domain knowledge for Ethernet switch testing, but their semi-structured format, implicit step attributes, and complex section dependencies make them difficult to directly leverage for test automation. To address this, we generate knowledge graphs (KGs) that capture configuration knowledge from ESCM in a structured form. We propose a multi-agent LLM-based framework that extracts, evaluates, and improves KGs from ESCMs using a fine-grained KG schema and an iterative Extract-Evaluate-Improve (EEI) loop. Our evaluation on 50 real-world ESCMs shows that our framework achieves high extraction correctness using the original prompts, with average correctness scores ranging from 0.97 to 0.99 across three extraction tasks. For challenging ESCMs, the EEI loop further improves correctness through manual-specific prompt refinement. Moreover, the LLM judgments and human evaluations show substantial agreement, with Cohen's kappa of at least 0.72 across all extraction tasks. Finally, feedback from industry testers indicates that the generated KGs can support the generation of useful and correct test case specifications (TCSs) for downstream testing.

cs.SE↗

arXiv2026

Characterizing the Failure Modes of LLMs in Resolving Real-World GitHub Issues

Large Language Models (LLMs) are increasingly deployed to resolve real-world GitHub issues. However, despite their potential, the specific failure modes of these models in complex repair tasks remain poorly understood. To characterize how LLM behavior diverges from human developer practices, this paper evaluates three state-of-the-art models, i.e., Claude 4.5 Sonnet, Gemini 3 Pro, and GPT-5, on the SWE-bench Verified dataset. We conduct a rigorous manual analysis of the symptoms and root causes underlying 243 failed attempts across 900 total trials. Our investigation first yields a unified failure taxonomy encompassing five distinct stages of the repair pipeline, within which we categorize typical failure symptoms and their prevalence. Secondly, our findings reveal that for all evaluated LLMs, strategy formulation and logic synthesis constitutes the most error-prone stage, followed by problem understanding, whereas localization exhibits the lowest failure rate. This suggests that LLMs may excel at fault localization, a task traditionally regarded as one of the most formidable challenges in automated program repair. Furthermore, we observe that robustness and operational costs (particularly in failure scenarios) vary significantly across different models. Finally, we uncover the root causes of these failures and propose actionable strategies to mitigate them. A particularly notable finding is that existing evaluation harnesses occasionally misjudge correct patches due to superficial discrepancies or hidden constraints. Collectively, our insights may provide promising directions for enhancing the effectiveness and reliability of LLM-based issue resolution.

cs.SE↗

arXiv2026

Mutation-Guided Unit Test Generation with a Large Language Model

Unit tests play a vital role in uncovering potential faults in software. While tools like EvoSuite focus on maximizing code coverage, recent advances in large language models (LLMs) have shifted attention toward LLM-based test generation. However, code coverage metrics -- such as line and branch coverage -- remain overly emphasized in reported research, despite being weak indicators of a test suite's fault-detection capability. In contrast, mutation score offers a more reliable and stringent measure, as demonstrated in our findings where some test suites achieve 100% coverage but only 4% mutation score. Although a few studies consider mutation score, the effectiveness of LLMs in killing mutants remains underexplored. In this paper, we propose MUTGEN, a mutation-guided, LLM-based test generation approach that incorporates mutation feedback directly into the prompt. Evaluated on 204 subjects from two benchmarks, MUTGEN significantly outperforms both EvoSuite and vanilla prompt-based strategies in terms of mutation score. Furthermore, MUTGEN introduces an iterative generation mechanism that pushes the limits of LLMs in killing additional mutants. Our study also provide insights into the limitations of LLM-based generation, analyzing the reasons for live and uncovered mutants, and the impact of different mutation operators on generation effectiveness.

cs.SE↗

arXiv2026

Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation

Unit testing plays a critical role in ensuring software correctness. However, writing unit tests manually is labor-intensive, especially for strongly typed languages like Java, motivating the need for automated approaches. Traditional methods primarily rely on search-based or randomized algorithms to achieve high code coverage and produce regression oracles, which are derived from the program's current behavior rather than its intended functionality. Recent advances in LLMs have enabled oracle generation from natural language descriptions, aligning better with user requirements. However, existing LLM-based methods often require fine-tuning or rely on external tools such as EvoSuite for test prefix generation, making them costly or cumbersome to apply in practice. In this work, we propose CANDOR, a novel prompt engineering-based LLM framework for automated unit test generation in Java. CANDOR orchestrates multiple specialized LLM agents to collaboratively generate complete tests. To mitigate the notorious hallucinations in LLMs and improve oracle correctness, we introduce a novel strategy that engages multiple reasoning LLMs in a panel discussion and generates accurate oracles based on consensus. Additionally, to reduce the verbosity of reasoning LLMs' outputs, we propose a novel dual-LLM pipeline to produce concise and structured oracle evaluations. Our experiments show that CANDOR is comparable with EvoSuite in generating tests with high code coverage and clearly superior in terms of mutation score. Moreover, our prompt engineering-based approach CANDOR significantly outperforms the SOTA fine-tuning-based oracle generator TOGLL by at least 21.1 percentage points in oracle correctness on both correct and faulty source code. Further ablation studies confirm the critical contributions of key agents in generating high-quality tests.

cs.SE↗

arXiv2026

Classifier or Prompt: A Case Study on Legal Requirements Traceability

New regulations are introduced to ensure software development aligns with ethical concerns and protects public safety. Showing compliance requires tracing requirements to legal provisions. Requirements traceability is a key task where engineers must analyze technical requirements against target artifacts, often within limited time. Manually analyzing complex systems with hundreds of requirements is infeasible. The legal dimension adds challenges that increase effort. In this paper, we investigate two automated solutions based on language models, including large ones (LLMs). The first solution, Kashif, is a classifier that leverages sentence transformers and semantic similarity. The second solution, RICE_LRT, prompts a recent LLM based on RICE, a prompt engineering framework. Using a publicly available benchmark dataset, we empirically evaluate Kashif and compare it against seven baseline classifiers from the literature (LSI, LDA, GloVe, TraceBERT, RoBERTa, and LLaMa). Kashif can identify trace links with F2 score of 63%, outperforming the best baseline by a substantial margin of 21 percentage points (pp) in F2 score. On a newly created and more complex requirements document traced to the European general data protection regulation (GDPR), RICE_LRT outperforms Kashif and baseline prompts in the literature by achieving an average recall of 84% and F2 score of 61%, improving the F2 score by 34 pp compared to the best baseline prompt. Our results indicate that requirements traceability in legal contexts cannot be adequately addressed by techniques proposed in the literature that are not specifically designed for legal artifacts. Furthermore, we demonstrate that our engineered prompt outperforms both classifier-based approaches and baseline prompts.

cs.SE↗