MedSkillAudit: Audit Framework for Medical AI Agent Skills
MedSkillAudit offers a domain-specific audit framework ensuring reliability and quality of AI agent skills in medical research.
Enhancing AI Reasoning with Self-Awareness to Reduce Errors
Discover how self-awareness in AI models mitigates logical inertia, improving reasoning accuracy and reliability in complex tasks.
Selective Forgetting Framework for Efficient AI Memory
Discover a biologically-inspired selective forgetting framework that boosts AI memory efficiency, quality, and security in large language model agents.
ActuBench: Multi-Agent LLM for Actuarial Task Evaluation
Discover ActuBench, a multi-agent LLM pipeline that automates generation and evaluation of actuarial reasoning tasks aligned with IAA standards.
Memory-Augmented LLM System for Auto Feature Generation
Discover MALMAS, a memory-augmented LLM multi-agent system for automated, high-quality feature generation on tabular data. Boost ML model accuracy now.