跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+979新增论文
+781其中 AI 相关
+119已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 07:14 — 2026-11-21 07:14(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

28,961 已收录论文24,030 AI 相关8,912 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 5 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.20033

The Hidden Methodological Layer: Uncovering Threats to Validity in LLM-Assisted Empirical Software Engineering

Victória Gomes, Fabio Palomba, Robert Feldt, Thomas Zimmermann, David Lo, Rodrigo Spinola

原文摘要

Context: Large Language Models (LLMs) are increasingly embedded in empirical software engineering (ESE) workflows, supporting tasks such as classification, coding, extraction, synthesis, and evaluation. Their probabilistic and opaque behavior, however, introduces methodological concerns that may affect empirical rigor. Aims: This paper investigates threats to validity introduced by LLM-assisted empirical workflows and examines how LLM interactions influence empirical studies. Method: We conducted a secondary analysis of 50 primary studies comprising 69 LLM-assisted research tasks identified through a systematic literature review. We examined the extent to which LLM-related threats were reported, how these threats were characterized, and how they related to established validity dimensions. Results: LLM-related threats remain substantially underreported. We identified recurring threats including classification errors, prompt-dependent interpretation, workflow instability, evaluator bias, downstream propagation of outputs, and model dependence. These threats can affect multiple validity dimensions depending on where and how LLM outputs enter the workflow. Conclusion: We introduce the concept of hidden methodological layer as a conceptual lens for understanding how LLMs influence empirical software engineering workflows. We argue that rigorous LLM-assisted ESE requires making prompts, model configurations, interaction protocols, validation procedures, and downstream reuse of LLM-generated outputs visible as part of the research method.

cs.SE

新论文 · v1arXiv:2611.13709

Do They Do as They Are Told? Investigating Coding Agents' Adherence to Explicit Instructions in Context Files

Gianmario Voria, Yutaro Kashiwa, Gemma Catolino, Fabio Palomba

原文摘要

Developers increasingly rely on agent context files (ACFs), persistent, project-scoped artifacts such as AGENTS.md, to steer the behavior of autonomous coding agents without renegotiating expectations at every interaction. Yet this governance mechanism rests on an untested assumption: that instructions written into an ACF are actually carried out, rather than ignored or loosely followed. Existing studies describe what ACFs contain, but not whether individual instructions are followed, leaving open which guidance can be trusted. We address this gap through an empirical study of real-world ACF snapshots and their linked agent-generated commits: characterizing the explicit, actionable instructions ACFs encode, operationalizing them into executable measurement scripts, and using these scripts to assess instruction-level compliance. We find that most observable instructions can be operationalized and that agents follow ACF guidance more often than not, but adherence splits sharply between instructions followed consistently and those never respected, with differences across instruction categories and coding agents. This split shows where ACF guidance works and where it does not, pointing to instruction types that may need rewriting and to agents that may need enforcement beyond the ACF. These findings lay the groundwork for systematic approaches to specifying, verifying, and enforcing project-specific instructions in autonomous software development.

cs.SE

版本更新 · v2arXiv:2502.04953

Automated Exploit and Security Test Generation: A Systematic Literature Review

Quang-Cuong Bui, Emanuele Iannone, Maria Camporese, Torge Hinrichs, Catherine Tony, László Tóth, Fabio Palomba, Péter Hegedűs 等 10 位作者

原文摘要

Static analysis techniques are often insufficient to determine whether a reported security vulnerability is exploitable and actually poses a real security risk to a software application. Dynamic analysis addresses this limitation by executing the target application with carefully crafted inputs that trigger or reproduce a given vulnerability. Over the past two decades, automatic exploit generation (AEG) and automatic security test generation (ASTG) have emerged as active research areas in cybersecurity and software engineering. This paper demystifies the field by establishing consistent terminology and presenting a systematic literature review (SLR) of research published in the last two decades. Starting from an initial set of 3,309 publications obtained from academic literature search engines, we selected and analyzed 71 papers comprising 67 distinct studies. We systematically compare existing AEG and ASTG approaches with respect to (i) the targeted software and vulnerability types, (ii) the generated artifacts, (iii) the underlying generation techniques and tools employed, (iv) the required inputs, (v) the evaluation methodologies, and (vi) implementation and tool availability.

cs.CR · cs.SE

新论文 · v1arXiv:2611.03231

Specification-Driven Governance for Fairness-by-Design in Agentic Software Engineering: How Far Can We Go?

Alfonso Cannavale, Alessandra Parziale, Valeria Pontillo, Patrizio Pelliccione, Andrea De Lucia, Fabio Palomba

原文摘要

Agentic AI is shifting developers' responsibilities from software implementation to software governance. While this paradigm improves productivity, it also raises challenges in ensuring that autonomous coding agents preserve developers' intentions. Among these, operationalizing fairness-by-design is largely unexplored, as existing approaches provide limited support for representing and propagating fairness requirements throughout agentic development workflows. In this paper, we investigate whether specification-driven development can operationalize fairness-by-design in the agentic development of machine learning systems. We study three coding agents on four machine learning applications, using four prompts that progressively operationalize fairness through nine Fairness Specification Elements, and analyze the traceability of fairness requirements across the generated artifacts, the fairness-accuracy trade-off of the resulting models, and the agents' design decisions and rationales. The results show that when fairness is operationalized, agents capture almost all fairness requirements in the specification (97.22%) and preserve most of them in the code (82.41%). However, the resulting models are not significantly fairer, as agents implement fairness as a post-hoc audit that neither shapes training nor prevents model delivery. Specifications thus make fairness traceable, but not enforceable, calling for fairness specifications that state what agents should do when requirements are not met, and for workflows that make the fairness decisions agents delegate to developers explicit.

cs.SE

新论文 · v1arXiv:2610.36363

Reliability-Aware Short-Term Glycemic Risk Prediction Using an Anchor-Based Comparative Framework of Sequence, Multimodal, and State-Updating Digital-Twin Models

Pir Bakhsh Khokhar, Carmine Gravino, Fabio Palomba

原文摘要

Anticipating short-term hypoglycemic and hyperglycemic risk is essential for proactive diabetes management. However, existing machine learning approaches often use inconsistent evaluation protocols and emphasize predictive performance over reliability. This study introduces an anchor-based benchmarking framework integrating longitudinal glucose sequences and multimodal patient information. Using the T1DiabetesGranada dataset, 5,503,441 standardized prediction anchors were constructed from 736 individuals with type 1 diabetes to evaluate hypoglycemia and hyperglycemia prediction at 30-, 60-, and 120-minute horizons. Three neural architectures, a Hybrid LSTM-Transformer, a Multimodal Digital Twin, and a State-Updating Digital Twin with gap-aware longitudinal state progression, were compared under identical patient-level validation protocols. Beyond predictive performance, the evaluation examined calibration, classification thresholds, explanation reliability, cross-model disagreement, and robustness to controlled perturbations. No statistically significant predictive differences were observed after Holm correction, although the models exhibited complementary reliability characteristics. The Multimodal Digital Twin achieved the lowest mean Brier score, while the State-Updating Digital Twin demonstrated the lowest mean expected calibration error (ECE-10). The Hybrid LSTM-Transformer showed strong explanation faithfulness and stability under its temporal attribution protocol. These findings highlight the importance of evaluating digital-twin models beyond predictive accuracy and emphasize the need for reliability assessment and external validation before clinical deployment.

cs.LG · cs.AI