Category
9,568 papers
AtomSearch is introduced, which keeps revision actions local while using subsequent skill states to guide search, and shows how local rule edits can support the exploration of useful revision paths and yield compact skills, with additional offline evaluations used to explore alternative states.
Self-distillation in agentic reinforcement learning has produced a growing number of methods. However, existing evaluations often reuse published baseline scores under differing experimental conditions, provide few direct comparisons among contemporaneous methods, and give limited attention to training stability and co...
The nature of improvement in each case is characterized: while recoverable concepts can be articulated through definitions and explanations, irrecoverable concepts cannot be transmitted, even with examples, and might require novel learning mechanisms.
Simulated students let researchers test tutoring systems and teaching strategies before real learners are available, but only if the simulation reproduces where a particular learner succeeds and fails. The common approach asks a large language model to role-play a student, but a role does not model what this learner kn...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Reinforcement learning provides a direct mechanism for optimizing task objectives in large language model-driven agents, but task rewards are typically sparse trajectory-level signals that only evaluate task success, without directly supervising action-conditioned environment transitions, leaving the model with limited...
We propose DAGFormer, a Transformer language model whose cross-layer connections are planned by a jointly trained topology predictor. Beyond the residual connections in a standard Transformer, DAGFormer adds direct connections from earlier layers to later ones, and the predictor controls the strength of every connectio...
As large language models (LLMs) are increasingly used to generate text, their misuse has become a growing societal problem, with implications for academic misconduct, model distillation, and cyberattacks. For these reasons, Model Authorship Attribution (MAA), which identifies the source model of a given text, is import...
The same recipe trained on a multi-domain corpus improves the frozen backbone on twelve evaluation benchmarks spanning mathematics, science, and commonsense, without task-specific adaptation.
This work presents an automated framework that classifies suspected overdoses from death investigation reports, while producing supporting explanations guided by expert knowledge, and shows that a pipeline model with explanations grounded in the input death investigation reports outperforms the other settings.
Typed decision models are language models that answer a question with a fixed set of possible answers by returning a probability for each answer instead of generating text. We study them on tabular data and compare four decision models with three large language models (LLMs) on row classification, fact verification and...
A unified framework that models both student responses to questions and tutor-posed subtasks during dialogues on a shared item response theory (IRT) scale is proposed and results show that the framework outperforms strong baselines on both question difficulty prediction and response correctness prediction.
Best-of-N sampling is a simple inference-time scaling strategy for large language models, yet its behavior under incomplete reward models remains poorly understood. We study Best-of-N as a competition between the extreme reward tails of correct and incorrect responses. This view shows that success depends not only on t...
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
