MAGMA (Agent / long-term memory): superseded — cited as a baseline and beaten by newer methods. 1 paper(s) critique it, 1 beat it on benchmarks — #30 of 63 most-superseded. Sub-problem: cluster led by Nemori. Newer alternatives in the same sub-problem include HAGE, SmartSearch.

Agent / long-term memory

MAGMA

MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents

Superseded baseline#30 of 63 most-superseded · first seen Apr 16, 2026

Superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 1 beat it on benchmarks

What papers say

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

Furthermore, even when continuous scores or edge weights are introduced, retrieval is still largely governed by fixed similarity search, manually designed scoring functions, or static heuristic traversal rules.

— HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution

Beaten on benchmarks

Head-to-head results where a newer method reports beating MAGMA. Values are copied from the source paper's tables — verify against the cited paper.

HAGE beats MAGMA
0.429 vs 0.337
F1 · [Qwen2.5-3B]
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.