EpiCon: shared multimodal memory lifts agent scores 1.7-4.9 points across 11 benchmarks

Ziyun Zeng · hf · 2026-09-30

EpiCon is a shared multimodal memory framework enabling collective agent learning without updating host model weights. It links per-question memory evolution to a persistent experience bank via two independently trained 2B models: a memory controller (jointly refining textual guidance and visual evidence) and a tree self-organizer (hierarchically consolidating lessons and retrieving experience/rules).

Original post →

More from coding & agent

coding & agent channel →