Related papers: Training AI Co-Scientists Using Rubric Rewards
Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction following tasks. However, existing methods predominantly rely on response-level…
The automated generation of research workflows is essential for improving the reproducibility of research and accelerating the paradigm of "AI for Science". However, existing methods typically extract merely fragmented procedural components…
While language models have shown remarkable performance across diverse tasks, they still encounter challenges in complex reasoning scenarios. Recent research suggests that language models trained on linearized search traces toward…
Automated scoring plays a crucial role in education by reducing the reliance on human raters, offering scalable and immediate evaluation of student work. While large language models (LLMs) have shown strong potential in this task, their use…
Scientific discovery is a complex cognitive process that has driven human knowledge and technological progress for centuries. While artificial intelligence (AI) has made significant advances in automating aspects of scientific reasoning,…
Challenges to reproducibility and replicability have gained widespread attention, driven by large replication projects with lukewarm success rates. A nascent work has emerged developing algorithms to estimate the replicability of published…
This review examines the role of artificial intelligence (AI) agents in programming education, focusing on how these tools are being integrated into educational practice and their impact on student learning outcomes. An analysis of…
As artificial intelligence becomes increasingly integrated into digital learning environments, the personalization of learning content to reflect learners' individual career goals offers promising potential to enhance engagement and…
Artificial intelligence systems are transforming scientific discovery by accelerating specific research tasks, from protein structure prediction to materials design, yet remain confined to narrow domains requiring substantial human…
Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a stronger model. However, this paradigm overlooks two fundamental factors: the…
This article explores the feasibility of creating an "electronic copy" of a deceased researcher by training artificial intelligence (AI) on the data stored in their personal computers. By analyzing typical data volumes on inherited…
Rubric-based text evaluation increasingly uses large language models (LLMs) as scalable judges, but aligning frozen black-box models with human scoring standards remains challenging. We formulate this challenge as a criteria-transfer…
This paper offers a roadmap for the development of scalable aligned artificial intelligence (AI) from first principle descriptions of natural intelligence. In brief, a possible path toward scalable aligned AI rests upon enabling artificial…
Can AI systems trained on the scientific record up to a fixed point in time forecast the scientific advances that follow? Such a capability could help researchers identify collaborators and impactful research directions, and anticipate…
Labeling data is essential for training text classifiers but is often difficult to accomplish accurately, especially for complex and abstract concepts. Seeking an improved method, this paper employs a novel approach using a generative…
Medical conversational AI (AI) plays a pivotal role in the development of safer and more effective medical dialogue systems. However, existing benchmarks and evaluation frameworks for assessing the information-gathering and diagnostic…
Training AI models in cybersecurity with help of vast datasets offers significant opportunities to mimic real-world behaviors effectively. However, challenges like data drift and scarcity of labelled data lead to frequent updates of models…
Many leading AI researchers expect AI development to exceed the transformative impact of all previous technological revolutions. This belief is based on the idea that AI will be able to automate the process of AI research itself, leading to…
As the complexity of modern workloads and hardware increasingly outpaces human research and engineering capacity, existing methods for database performance optimization struggle to keep pace. To address this gap, a new class of techniques,…
The rapid expansion of scholarly literature presents significant challenges in synthesizing comprehensive, high-quality academic surveys. Recent advancements in agentic systems offer considerable promise for automating tasks that…