Agent / long-term memory
MIRIX
MIRIX: Multi-Agent Memory System for LLM-Based Agents
Superseded baseline#17 of 63 most-superseded · first seen Jul 10, 2025
Superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 2 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites MIRIX as a baseline.
they operate in an ``open loop'' without feedback on whether the constructed memories benefit downstream tasks
Beaten on benchmarks
Head-to-head results where a newer method reports beating MIRIX. Values are copied from the source paper's tables — verify against the cited paper.
MemBuilder beats MIRIX
85.75 vs 73.25
accuracy · [LongMemEval benchmark]
MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards
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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.