Pull request (PR) descriptions generated by AI coding agents are the primary channel for communicating code changes to human reviewers. However, the alignment between these messages and the actual changes remains unexplored, raising concerns about the trustworthiness of AI agents. To fill this gap, we analyzed 23,247 agentic PRs across five agents using PR message-code inconsistency (PR-MCI). We contributed 974 manually annotated PRs, found 406 PRs (1.7%) exhibited high PR-MCI, and identified eight PR-MCI types, revealing that descriptions claim unimplemented changes was the most common issue (45.4%). Statistical tests confirmed that high-MCI PRs had 51.7% lower acceptance rates (28.3% vs. 80.0%) and took 3.5 × longer to merge (55.8 vs. 16.0 hours). Our findings suggest that unreliable PR descriptions undermine trust in AI agents, highlighting the need for PR-MCI verification mechanisms and improved PR generation to enable trustworthy human-AI collaboration.

The rapid adoption of AI-powered coding assistants is transforming software development practices, yet systematic comparisons of their effectiveness across different task types and over time remain limited. This paper presents an empirical study comparing five popular agents (OpenAI Codex, GitHub Copilot, Devin, Cursor, and Claude Code), analyzing 7,156 pull requests (PRs) from the AIDev dataset. Temporal trend analysis reveals heterogeneous evolution patterns: Devin exhibits the only consistent positive trend in acceptance rate (+0.77% per week over 32 weeks), whereas other agents remain largely stable. Our analysis suggests that the PR task type is a dominant factor influencing acceptance rates: documentation tasks achieve 82.1% acceptance compared to 66.1% for new features—a 16 percentage point gap that exceeds typical inter-agent variance for most tasks. OpenAI Codex achieves consistently high acceptance rates across all nine task categories (59.6%–88.6%), with stratified Chi-square tests confirming statistically significant advantages over other agents in several task categories. However, no single agent performs best across all task types: Claude Code leads in documentation (92.3%) and features (72.6%), while Cursor excels in fix tasks (80.4%).

There is a growing interest in leveraging multiple large language models (LLMs) for automated code optimization. However, industrial platforms deploying multiple LLMs face a critical challenge: prompts optimized for one LLM often fail with others, requiring expensive model-specific prompt engineering. This cross-model prompt engineering bottleneck severely limits the practical deployment of multi-LLM systems in production environments. We introduce Meta-Prompted Code Optimization (Mpco), a framework that automatically generates high-quality, task-specific prompts across diverse LLMs while maintaining industrial efficiency requirements. Mpco leverages meta-prompting to dynamically synthesize context-aware optimization prompts by integrating project metadata, task requirements, and LLM-specific contexts. It is an essential part of the ARTEMIS code optimization platform for automated validation and scaling.Our comprehensive evaluation on five real-world codebases with 366 hours of runtime benchmarking demonstrates Mpco’s effectiveness: it achieves overall performance improvements up to 19.06% with the best statistical rank across all systems compared to baseline methods. Analysis shows that 96% of the top-performing optimizations stem from meaningful edits. Through systematic ablation studies and meta-prompter sensitivity analysis, we identify that comprehensive context integration is essential for effective meta-prompting and that major LLMs can serve effectively as meta-prompters, providing actionable insights for industrial practitioners.

Performance is arguably the most crucial attribute that reflects the quality of a configurable software system. However, given the increasing scale and complexity of modern software, modeling and predicting how various configurations can impact performance becomes one of the major challenges in software maintenance. As such, performance is often modeled without having a thorough knowledge of the software system, but relying mainly on data, which fits precisely with the purpose of deep learning. In this article, we conduct a comprehensive review exclusively on the topic of deep learning for performance learning of configurable software, covering 1,206 searched papers spanning six indexing services, based on which 99 primary papers were extracted and analyzed. Our results outline key statistics, taxonomy, strengths, weaknesses, and optimal usage scenarios for techniques related to the preparation of configuration data, the construction of deep learning performance models, the evaluation of these models, and their utilization in various software configuration-related tasks. We also identify the good practices and potentially problematic phenomena from the studies surveyed, together with a comprehensive summary of actionable suggestions and insights into future opportunities within the field. To promote open science, all the raw results of this survey can be accessed at our repository: https://github.com/ideas-labo/DCPL-SLR .

To ease the expensive measurements during configuration tuning, it is natural to build a surrogate model as the replacement of the system, and thereby the configuration performance can be cheaply evaluated. Yet, a stereotype therein is that the higher the model accuracy, the better the tuning result would be, or vice versa. This “accuracy is all” belief drives our research community to build more and more accurate models and criticize a tuner for the inaccuracy of the model used. However, this practice raises some previously unaddressed questions, e.g., are the model and its accuracy really that important for the tuning result? Do those somewhat small accuracy improvements reported (e.g., a few % error reduction) in existing work really matter much to the tuners? What role does model accuracy play in the impact of tuning quality? To answer those related questions, in this paper, we conduct one of the largest-scale empirical studies to date-running over the period of 13 months 24 × 7-that covers 10 models, 17 tuners, and 29 systems from the existing works while under four different commonly used metrics, leading to 13,612 cases of investigation. Surprisingly, our key findings reveal that the accuracy can lie: there are a considerable number of cases where higher accuracy actually leads to no improvement in the tuning outcomes (up to 58% cases under certain setting), or even worse, it can degrade the tuning quality (up to 24% cases under certain setting). We also discover that the chosen models in most proposed tuners are sub-optimal and that the required % of accuracy change to significantly improve tuning quality varies according to the range of model accuracy. From those, we provide in-depth discussions of the rationale behind and offer several lessons learned as well as insights for future opportunities. Most importantly, this work poses a clear message to the community: we should take one step back from the natural "accuracy is all" belief for model-based configuration tuning.

Machine/deep learning models have been widely adopted to predict the configuration performance of software systems. However, a crucial yet unaddressed challenge is how to cater for the sparsity inherited from the configuration landscape: the influence of configuration options (features) and the distribution of data samples are highly sparse. In this paper, we propose a model-agnostic and sparsity-robust framework for predicting configuration performance, dubbedDaL, based on the new paradigm of dividable learning that builds a model via “divide-and-learn”. To handle sample sparsity, the samples from the configuration landscape are divided into distant divisions, for each of which we build a sparse local model, e.g., regularized Hierarchical Interaction Neural Network, to deal with the feature sparsity. A newly given configuration would then be assigned to the right model of division for the final prediction. Further,DaLadaptively determines the optimal number of divisions required for a system and sample size without any extra training or profiling. Experiment results from 12 real-world systems and five sets of training data reveal that, compared with the state-of-the-art approaches,DaLperforms no worse than the best counterpart on 44 out of 60 cases (within which 31 cases are significantly better) with up to$1.61\times$improvement on accuracy; requires fewer samples to reach the same/better accuracy; and producing acceptable training overhead. In particular, the mechanism that adapted the parameter$d$can reach the optimal value for 76.43% of the individual runs. The result also confirms that the paradigm of dividable learning is more suitable than other similar paradigms such as ensemble learning for predicting configuration performance. Practically,DaLconsiderably improves different global models when using them as the underlying local models, which further strengthens its flexibility. To promote open science, all the data, code, and supplementary materials of this work can be accessed at our repository:https://github.com/ideas-labo/DaL-ext.

Predicting the performance of highly configurable software systems is the foundation for performance testing and quality assurance. To that end, recent work has been relying on machine/deep learning to model software performance. However, a crucial yet unaddressed challenge is how to cater for the sparsity inherited from the configuration landscape: the influence of configuration options (features) and the distribution of data samples are highly sparse.

Learning and predicting the performance of a configurable software system helps to provide better quality assurance. One important engineering decision therein is how to encode the configuration into the model built. Despite the presence of different encoding schemes, there is still little understanding of which is better and under what circumstances, as the community often relies on some general beliefs that inform the decision in an ad-hoc manner. To bridge this gap, in this paper, we empirically compared the widely used encoding schemes for software performance learning, namely label, scaled label, and one-hot encoding. The study covers five systems, seven models, and three encoding schemes, leading to 105 cases of investigation.