Structured Reasoning Provenance for Autonomous AI Agents
Discover how structured reasoning provenance enhances autonomous AI agents with actionable behavioral analytics beyond checkpoints and traces.
PACED: Optimized Distillation for Advanced AI Learning
Discover PACED, a cutting-edge distillation method that boosts AI model training by focusing on student competence and improving efficiency.
ReplicatorBench: Benchmarking AI for Research Replicability
Discover ReplicatorBench, a benchmark testing AI agents' ability to replicate social and behavioral science research with real-world data challenges.
H-AdminSim: Realistic Hospital Workflow Simulator with FHIR
Explore H-AdminSim, a multi-agent simulator enhancing hospital admin workflows with FHIR integration for efficient healthcare operations and automation.
Benchmarking LLMs on Natural Language Combinatorial Optimization
Explore how large language models perform on natural-language combinatorial optimization tasks using the new NLCO benchmark framework.