Agent / long-term memory
Present, but with little supersession signal in the knowledge base
0 papers critique it · 1 beat it on benchmarks
Head-to-head results where a newer method reports beating MiroFlow. Values are copied from the source paper's tables — verify against the cited paper.
Live-Evo beats MiroFlow
0.14 vs 0.32
Avg · [Deep Research Methods]
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.