Researchers have proposed a new method called SkillGate to improve the performance of long-horizon agents in decision-making tasks. These agents use s...
Researchers have developed DentAgent, a multi-agent framework for dental reasoning that integrates evidence from various sources. The system consists ...
Researchers have developed a protocol called EvoResearcher that allows large language models to perform self-reflection and early stopping without req...
Researchers have developed a new algorithm called Class Expression Simplifier (CES) to simplify complex OWL class expressions. These expressions are u...
Researchers have developed a testing framework called TestifAI to evaluate the robustness of deep learning models against various types of perturbatio...
Researchers have found that vision language models (VLMs) can be easily manipulated by adding small, imperceptible changes to visual inputs. This make...
Researchers have proposed a new theory of post-hoc debate judgement for artificial intelligence systems. Debates are used to improve performance and e...
Researchers have developed a method for using large language models to extract nuanced information from research articles. They tested four workflows,...
Researchers have developed an adaptive memory and reflection multi-agent system for medical question answering. This system uses specialized agents wi...
Researchers have developed a new AI architecture called Eureka that can tackle complex scientific tasks by forming dynamic obligation graphs. This all...
Researchers from various institutions analyzed post-training trajectories of large language models and found that these agents tend to stick to a sing...
Researchers have proposed a new risk measure called the Wasserstein entropic value-at-risk. This measure is designed to capture an agent's uncertainty...