Related papers: CAPE: Capability Achievement via Policy Execution
Adaptive learning often diagnoses precisely yet intervenes weakly, yielding help that is mistimed or misaligned. This study presents evidence supporting an instructor-governed feedback loop that converts concept-level assessment evidence…
A key hurdle is demonstrating compute resource capability with limited benchmarks. We propose workflow templates as a solution, offering adaptable designs for specific scientific applications. Our paper identifies common usage patterns for…
Large-scale general domain pretraining followed by downstream-specific finetuning has become a predominant paradigm in machine learning. However, discrepancies between the pretraining and target domains can still lead to performance…
For an explanation of a deep learning model to be effective, it must provide both insight into a model and suggest a corresponding action in order to achieve some objective. Too often, the litany of proposed explainable deep learning…
Preference handling and optimization are indispensable means for addressing non-trivial applications in Answer Set Programming (ASP). However, their implementation becomes difficult whenever they bring about a significant increase in…
One important challenge for a set of agents to achieve more efficient collaboration is for these agents to maintain proper models of each other. An important aspect of these models of other agents is that they are often partial and…
Generative AI systems achieve impressive performance on standard benchmarks yet fail to deliver real-world utility, a disconnect we identify across 28 deployment cases spanning education, healthcare, software engineering, and law. We argue…
The rise of autonomous AI agents exposes a fundamental flaw in API-centric architectures: probabilistic systems directly execute state mutations without sufficient context, coordination, or safety guarantees. We introduce OpenKedge, a…
Agile software development evolves so rapidly that research struggles to remain timely and transferable - an issue heightened by the swift adoption of generative AI and agentic tools. Earlier discussions highlight theory and time gaps,…
General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…
Large Language Model (LLM) agents are increasingly deployed in complex, multi-step workflows involving planning, tool use, reflection, and interaction with external knowledge systems. These workflows generate rapidly expanding contexts that…
Automatic post-editing (APE) aims to refine machine translations by correcting residual errors. Although recent large language models (LLMs) demonstrate strong translation capabilities, their effectiveness for APE--especially under…
Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by trajectory-opaque grading, underspecified safety and…
We present recent advances in formal verification and control for autonomous systems with practical safety guarantees enabled by conformal prediction (CP), a statistical tool for uncertainty quantification. This survey is particularly…
In research of manufacturing systems and autonomous robots, the term capability is used for a machine-interpretable specification of a system function. Approaches in this research area develop information models that capture all information…
Pretrained code language models have enabled great progress towards program synthesis. However, common approaches only consider in-file local context and thus miss information and constraints imposed by other parts of the codebase and its…
Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…
In the field of machine learning, ensemble learning is widely recognized as a pivotal strategy for pushing the boundaries of predictive performance. Traditional static ensemble methods typically assign weights by treating each base learner…
CodeLLMs have demonstrated remarkable advancements in software engineering tasks. However, while these models can generate functionally correct code, they often produce code that is inefficient in terms of runtime. This inefficiency is…
Explainability of a classification model is crucial when deployed in real-world decision support systems. Explanations make predictions actionable to the user and should inform about the capabilities and limitations of the system. Existing…