AI RESEARCH
SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs
arXiv CS.AI
•
ArXi:2512.04868v2 Announce Type: replace-cross Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual dependencies, and executing complex logical reasoning. Existing approaches often suffer from inaccuracies and prohibitive computational costs, particularly when processing intricate queries over large knowledge graphs.