#artificial intelligence
Sep 2026
RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent
This work proposes RefCon, which combines sequential self-refinement with parallel self-contrast to extract higher-quality memories without gold labels, and generalizes across model scales and to software engineering tasks, where it surpasses even ground-truth baselines.
Ubaidillah Ariq Prathama, Bo Liu, Yeonsun Hong et al.
· arXiv.org · 0 citations