KEEPER2 min read
KEEPER: Learning Control-Sufficient Textual Memory for Long-Horizon LLM Agents
Recursive textual memory can carry earlier errors into later updates, yet task performance alone does not establish memory reliability. We define self-consistency bias as the persistence of incorrect claims already present in the incoming memory.
By Jinkyeong Choi, Chaebin Jeong, Junsung Jeon, Donghyeon ParkarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Nov 2, 2026.
Comments
Sign in to join the discussion.