Related papers: SkillClone: Multi-Modal Clone Detection and Clone …

We consider the well-known and important tasks of clone detection and information retrieval for source code. The most standard setup is to search clones inside the same language code snippets. But it is also useful to find code snippets…

Behavioural cloning has been extensively used to train agents and is recognized as a fast and solid approach to teach general behaviours based on expert trajectories. Such method follows the supervised learning paradigm and it strongly…

Software vulnerabilities (SVs) pose a critical threat to safety-critical systems, driving the adoption of AI-based approaches such as machine learning and deep learning for software vulnerability detection. Despite promising results, most…

Multimodal large language models have unlocked new possibilities for various multimodal tasks. However, their potential in image manipulation detection remains unexplored. When directly applied to the IMD task, M-LLMs often produce…

Equipping Large Language Model (LLM) agents with domain-specific skills is critical for tackling complex tasks. Yet, manual authoring creates a severe scalability bottleneck. Conversely, automated skill generation often yields fragile or…

The companion paper introduced a four-level verification lattice on agent-skill manifests (unverified, declared, tested, formal) and left the top level aspirational. This paper closes that gap. We give a precise semantics for skill…

Large Language Models (LLMs) have achieved impressive results on static code-generation benchmarks, but real-world software development unfolds as a continuous stream of evolving issues, fixes, and feature requests. We introduce…

Behavioural cloning is an imitation learning technique that teaches an agent how to behave via expert demonstrations. Recent approaches use self-supervision of fully-observable unlabelled snapshots of the states to decode state pairs into…

Co-change candidates are the group of code fragments that require a change if any of these fragments experience a modification in a commit operation during software evolution. The cloned co-change candidates are a subset of the co-change…

AI agents are systems capable of perceiving their environment, autonomously planning and executing tasks. Recent advancements in LLM have introduced a transformative paradigm for AI agents, enabling them to interact with external resources…

Documenting tacit knowledge in organizations can be a challenging task due to incomplete initial information, difficulty in identifying knowledgeable individuals, the interplay of formal hierarchies and informal networks, and the need to…

Language models (LMs) have achieved impressive accuracy across a variety of tasks but remain vulnerable to high-confidence misclassifications, also referred to as unknown unknowns (UUs). These UUs cluster into blind spots in the feature…

Machine learning (ML) enables accurate and fast molecular property predictions, which are of interest in drug discovery and material design. Their success is based on the principle of similarity at its heart, assuming that similar molecules…

Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the quality of the offline dataset, such pre-trained agents may…

Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models, trained on extensive datasets that include code…

Training large language models to acquire specific skills remains a challenging endeavor. Conventional training approaches often struggle with data distribution imbalances and inadequacies in objective functions that do not align well with…

Recent studies show that LLMs possess different skills and specialize in different tasks. In fact, we observe that their varied performance occur in several levels of granularity. For example, in the code optimization task, code LLMs excel…

LLM agents are rapidly becoming the practical interface for task automation, yet the ecosystem lacks a principled way to choose among an exploding space of deployable configurations. Existing LLM leaderboards and tool/agent benchmarks…

Relying on multi-modal observations, embodied robots (e.g., humanoid robots) could perform multiple robotic manipulation tasks in unstructured real-world environments. However, most language-conditioned behavior-cloning agents in robots…

Misinformation can be countered with fact-checking, but the process is costly and slow. Identifying checkworthy claims is the first step, where automation can help scale fact-checkers' efforts. However, detection methods struggle with…