Related papers: The Productivity-Reliability Paradox: Specificatio…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within…

Fine-tuning large language models (LLMs) often causes overfitting to specific prompt wording, where minor phrasing variations drastically reduce performance. To address this, we propose Prompt-Agnostic Fine-Tuning (PAFT), a method that…

This longitudinal pilot study tracked how generative AI reshapes problem-solving over six months across three waves in an academic setting. AI integration reached saturation by Wave 3, with daily use rising from 52.4% to 95.7% and ChatGPT…

Retrieval Augmented Generation (RAG) improves correctness of Question Answering (QA) and addresses hallucinations in Large Language Models (LLMs), yet greatly increase computational costs. Besides, RAG is not always needed as may introduce…

AI coding agents increasingly submit pull requests (Agentic-PRs) to open-source repositories, yet their performance is commonly assessed using merge and rejection outcomes alone. We hypothesized that these outcome labels do not reliably…

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

Large Language Models (LLMs) are prone to hallucination, especially during multi-hop and reasoning-intensive tasks such as mathematical problem solving. While Outcome Reward Models verify only final answers, Process Reward Models (PRMs)…

Process reward models (PRMs) that provide dense, step-level feedback have shown promise for reinforcement learning, yet their adoption remains limited by the need for expensive step-level annotations or ground truth references. We propose…

Despite productivity increasing eightfold since Keynes's 1930 prediction of 15-hour workweeks, workers globally still work roughly double these hours. Separately, AI development accelerates despite existential risk warnings from leading…

Software Engineering 3.0 marks a paradigm shift in software development, in which AI coding agents are no longer just assistive tools but active contributors. While prior empirical studies have examined productivity gains and acceptance…

Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs) within static domains such as mathematics. However, their potential in dynamic data analysis tasks…

Existing AI alignment approaches assume that preferences are static, which is unrealistic: our preferences change, and may even be influenced by our interactions with AI systems themselves. To clarify the consequences of incorrectly…

Agentic Retrieval-Augmented Generation (Agentic RAG) enhances the processing capability for complex tasks through dynamic retrieval and adaptive workflows. Recent advances (e.g., Search-R1) have shown that outcome-supervised reinforcement…

Since software performance requirements are documented in natural language, quantifying them into mathematical forms is essential for software engineering. Yet, the vagueness in performance requirements and uncertainty of human cognition…

Tiny Recursive Models (TRM) were proposed as a parameter-efficient alternative to large language models for solving Abstraction and Reasoning Corpus (ARC) style tasks. The original work reports strong performance and suggests that recursive…

Requirements traceability, the process of establishing and maintaining relationships between requirements and various software development artifacts, is paramount for ensuring system integrity and fulfilling requirements throughout the…

Retrieval-augmented generation (RAG) generally enhances large language models' (LLMs) ability to solve knowledge-intensive tasks. But RAG may also lead to performance degradation due to imperfect retrieval and the model's limited ability to…

Autonomous coding agents (e.g., OpenAI Codex, Devin, GitHub Copilot) are increasingly used to generate fix-related pull requests (PRs) in real world software repositories. However, their practical effectiveness depends on whether these…

Deploying large language model-based code generation in real-world client-side development remains challenging due to heterogeneous inputs, strict engineering constraints, and complex interaction logic expressed in product requirement…

Context. AI-based development tools, such as GitHub Copilot, are transforming the software development process by offering real-time code suggestions. These tools promise to improve the productivity by reducing cognitive load and speeding…