Is Memory-R1 superseded?

Memory-R1 (Agent / long-term memory): superseded — cited as a baseline and beaten by newer methods. 4 paper(s) critique it, 1 beat it on benchmarks — #12 of 63 most-superseded. Sub-problem: cluster led by Mem0. Newer alternatives in the same sub-problem include REAL, MemPro, MemGuard, DeferMem, Memory-R2.

Method Drift›Agent / long-term memory

Superseded baseline#12 of 63 most-superseded

Memory-R1

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

Agent / long-term memory · first seen Aug 27, 2025

superseded — cited as a baseline and beaten by newer methods

4 papers critique it · 1 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites Memory-R1 as a baseline.

“Memory-R1 introduces a comprehensive forgetting mechanism similar to the one we propose, but lacks any kind of temporal encoding in its stored memories.”
— Mnemosyne: An Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs
“While Memory-R1~memoryr1 advances this by using reinforcement learning to optimize storage and retrieval policies, its retrieval is still a single-round process.”
— General Agentic Memory Via Deep Research
“In long-term dialogues, a single reward given at the end of a multi-session trajectory is too sparse.”
— MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards
“However, they rely mainly on outcome-level rewards and do not explicitly address cross-session credit assignment under diverging memory states.”
— Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents

Beaten on benchmarks

Head-to-head results where a newer method reports beating Memory-R1. Values are copied from the source paper's tables — verify against the cited paper.

Memory-R2 beats Memory-R1 · F1 [Multi-hop]
38.41 vs 33.64
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · B1 [Multi-hop]
30.90 vs 26.06
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · J [Multi-hop]
80.93 vs 62.34
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · J [Open Domain]
67.53 vs 40.96
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · F1 [Single Hop]
54.06 vs 46.86
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · B1 [Single Hop]
48.73 vs 40.92
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · J [Single Hop]
86.80 vs 67.81
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · F1 [Temporal]
59.65 vs 47.75
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · B1 [Temporal]
50.05 vs 38.49
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · J [Temporal]
69.90 vs 49.61
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · F1 [Overall]
50.60 vs 43.14
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 beats Memory-R1 · B1 [Overall]
44.01 vs 36.44
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents

Newer alternatives

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