Is MemSkill superseded?

MemSkill (Agent / long-term memory): superseded — cited as a baseline and beaten by newer methods. 2 paper(s) critique it, 1 beat it on benchmarks — #19 of 63 most-superseded. Sub-problem: cluster led by Nemori. Newer alternatives in the same sub-problem include HAGE, SmartSearch, event-centric memory.

Method Drift›Agent / long-term memory

Superseded baseline#19 of 63 most-superseded

MemSkill

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

Agent / long-term memory · first seen Feb 2, 2026

superseded — cited as a baseline and beaten by newer methods

2 papers critique it · 1 beat it on benchmarks

What papers say

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

“However, most existing agent-memory approaches still rely on unweighted or weakly weighted relations, where an edge primarily indicates the existence of a connection rather than its query-dependent utility.”
— HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
“These approaches use smaller ML models rather than full LLMs for structuring, but still require task-specific training data and GPU inference during ingestion or search.”
— SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval

Beaten on benchmarks

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

HAGE beats MemSkill · Overall [gpt-4o-mini]
0.739 vs 0.501
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE beats MemSkill · Overall [Qwen2.5-3B]
0.548 vs 0.179
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE beats MemSkill · LLM Score [GPT-4o-mini]
0.824 vs 0.779
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE beats MemSkill · F1 [GPT-4o-mini]
0.678 vs 0.579
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE beats MemSkill · LLM Score [Qwen2.5-3B]
0.527 vs 0.247
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE beats MemSkill · F1 [Qwen2.5-3B]
0.429 vs 0.179
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE beats MemSkill · Avg. Score [all]
0.739 vs 0.501
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.