Benchmarking Continual Agent Memory for Online Learning, Transfer, and Forgetting

Jan 2, 2026·
Zihang Ma
*
,
Jinyi Liu
Jinyi Liu
*
,
Hongyao Tang
,
Yi Ma
,
Ruitao Wang
,
Yifu Yuan
,
Yan Zheng
,
Jianye Hao
· 0 min read
Type
Publication
LLA@ICLR 2026 Poster

Overview

AgentMemoryBench is a unified benchmark for continual agent memory that measures improvement, retention, forgetting, transfer, and conflict resolution over time, together with a multi-memory baseline called MEMs.

Venue. LLA@ICLR 2026 Poster

LLM Agent Memory Continual Learning Benchmark LLA 2026
Jinyi Liu
Authors
Jinyi Liu
Ph.D. Candidate Reinforcement Learning and LLM Systems
Back to Publications

More Publications

Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language Model Jan 2026 CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis Jan 2026 From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation Jan 2026