Fred Sun

DACG-agent is presented, a drift-aware causal-graph agent that incrementally builds a causal knowledge graph from PubMed abstracts and applies a two-layer stopping policy with complementary roles: a KL-divergence monitor that detects posterior convergence (the accuracy layer), and a Bradley--Terry process reward model (PRM) whose online decline detection halts retrieval once evidence quality peaks (the efficiency layer).

A time-aligned evolving concept graph framework that jointly models semantic and structural evolution and pair-level fusion combines these states to forecast first co-occurrence, relation formation, and conditional relation type is proposed.