AI
Candidate-Fate Accounting for Transparent Sensor Diagnostic Pipeline Search
Researchers propose a framework called candidate-fate accounting to improve transparency in automate...
AI
Sanyu Studio: A Multi-Agent System for Art-Historical Narrative Construction
Researchers have developed a multi-agent system called Sanyu Studio to explore how generative AI can...
AI
RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training
A new method called Reverse-Turn Policy Optimization (RTPO) has been proposed to stabilize the train...
AI
Competence, Not Accuracy: A Diagnostic for Reference-Free Judge Gates in Skill Optimization
Researchers have developed a diagnostic tool to evaluate the performance of 'judge gates' in skill o...
AI
A Multi-Agent Platform for Automated Enterprise Analytics and Insight Generation
A new multi-agent platform for automated enterprise analytics has been proposed....
AI
Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots
Researchers have developed an automatic metric evaluator called EvalCEGAR that c...
AI
Pairwise Logical Selection of Enthymeme Completions under Semantic-Link Uncertainty
Researchers have developed a new method called Possible-World Atom-Link Formaliz...
AI
Verifiable abstention makes AI leak diagnosis accountable in water distribution networks
Researchers have developed a method to make AI-powered leak diagnosis in water d...