Agent / long-term memory

AriGraph

AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents

Superseded baseline#46 of 63 most-superseded · first seen Jul 5, 2024

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites AriGraph as a baseline.

tailored for text-based games with discrete state transitions, which are rarely present in the ambiguous boundaries of natural conversation.
GAM: Hierarchical Graph-based Agentic Memory for LLM Agents

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.