All AI memory papers

Phonetic Trajectory Memory (PTM) combines the Acoustic Injection, Entropy Filter, Neuro-Symbolic Relay, and Resonance Engine to encode text as a continuous trajectory on an ergodic Hyper-Torus Memory instead of a growing KV cache. PTM delivers >3,000× signal-to-KV compression while maintaining ≈92% factual accuracy and sub-50 ms retrieval latency on long narrative and scientific corpora compared to dense KV baselines.

DM-RAG augments Phi-4-mini with a Short-Term Memory (STM) buffer, Long-Term Memory (LTM) FAISS store, Bayesian fusion, and a logistic regression confidence model for structured log analysis. On UNSW-NB15, DM-RAG reaches 98.70% recall and 69.59% F1, beating the Phi-4 + RAG (MITRE) baseline in F1 by 17.89 points.

Memory-Augmented Transformers organizes functional objectives, memory types, and integration techniques into a unified taxonomy that connects biological memory principles with concrete architectures like Memformer, Titans, ATLAS, and EMAT. Memory-Augmented Transformers’ main result is a systematic three-dimensional classification that links dynamic multi-timescale memory, selective attention, and consolidation to specific Transformer designs and emerging lifelong-learning paradigms.

MemoryBench orchestrates Task Provider, User Simulator, and Performance Monitor to feed heterogeneous tasks, simulate explicit and implicit feedback, and score LLM systems across declarative and procedural memory. MemoryBench’s main finding is that state-of-the-art memory systems like A-Mem, Mem0, and MemoryOS often fail to beat naive BM25 or embedding-based RAG on partitions such as SiLo and LiLo.

Memory Decoder combines a Pre-training stage that aligns with kNN-LM distributions and an Inference interpolation mechanism that mixes Memory Decoder and base LLM outputs without changing base parameters. On Wikitext-103, Memory Decoder with 124M parameters reaches 13.36 perplexity on GPT2-small versus 14.76 for DAPT, and on specialized domains a single 0.5B Memory Decoder reduces average perplexity from 14.88 to 4.05 on Qwen2-0.5B.

MemVid combines a memory model, memorizer, retriever, and generator so a reasoning-oriented KV-cache memory can produce task-specific clues that drive video moment retrieval. On VideoMME (with subtitles, Avg column), MemVid scores 65.7% compared to 61.0% for Video-XL-7B, a +4.7 point gain under the same 7B scale.

Memory in Large Language Models defines LLM memory via a memory quadruple, a three-regime evaluation protocol, and four memory types: parametric, contextual, external, and procedural/episodic. Memory in Large Language Models’ main result is a deployment-oriented framework that connects mechanisms, layered evaluation, and DMM-Gov dynamic governance into a reproducible, comparable baseline for RAG systems.

Memory in the Age of AI Agents formalizes agent memory with Memory Formation, Memory Evolution, and Memory Retrieval operators, and classifies memories into token-level, parametric, and latent forms plus factual, experiential, and working functions. Memory in the Age of AI Agents’ main result is a unified Forms–Functions–Dynamics framework that consolidates fragmented LLM agent memory work, benchmarks, and open-source frameworks into a coherent taxonomy.

Memory-R1 equips LLM agents with a Memory Manager, Answer Agent, Memory Distillation policy, and PPO/GRPO-based RL training to manage ADD, UPDATE, DELETE, and NOOP operations over an external memory bank. On LoCoMo with LLaMA-3.1-8B-Instruct, Memory-R1-GRPO reaches 45.02 F1, 37.51 BLEU-1, and 62.74 LLM-as-a-Judge versus MemoryOS at 35.04 F1, 27.99 BLEU-1, and 48.20.

MemOS standardizes memory as MemCube units orchestrated by MemReader, MemScheduler, MemLifecycle, MemOperator, MemVault, and MemGovernance to manage parametric, activation, and plaintext memory as one system. MemOS does not report benchmark numbers but instead contributes a unified architecture and Memory Interchange Protocol for cross-LLM memory sharing and lifecycle governance.

Mem-PAL uses Log Graph, Background, Topic Outline, and Principle memories to encode long-term user logs and dialogues into structured, retrievable personas. On PAL-Bench’s Requirement Restatement task, H2Memory in Mem-PAL achieves a GPT-4 G-Score of 32.54, +3.21 over Session-level RAG, and boosts BLEU-1 to 26.67 vs 23.81.

Memp constructs agent skills via Build, Retrieve, and Update modules that turn past trajectories into scripts, trajectories, and combined proceduralizations stored in a procedural memory library. On ALFWorld, Memp’s proceduralization with GPT-4o reaches 77.86% test success versus 42.14% with no memory, while reducing steps from 23.76 to 15.01.

MEMTRACK evaluates long term memory by combining a Containerized Environment, Timeline Generator, Event Parser, and Execution Monitoring with multi platform tools like Slack, Linear, and Git. On the MEMTRACK benchmark, the best performing GPT 5 configuration achieves only a 60% Correctness score, revealing substantial room for improvement over existing memory backends.

MEPIC extends vLLM with a Chunk Cache Coordinator, Chunk Matcher, Hybrid KV Manager, Chunk LRU Manager, and Chunk Processor to manage canonical, page-aligned, position-independent KV chunks in HBM. On long-context workloads, MEPIC reduces HBM usage by up to 5.21× and lowers latency by up to 11.48% compared to CacheBlend on Mistral-7B-Instruct-v0.3.

MeVe decomposes retrieval into Initial Retrieval, Relevance Verification, Fallback Retrieval, Context Prioritization, and Token Budgeting to tightly control what enters the LLM context. On a Wikipedia subset and HotpotQA, MeVe reduces average context from 188.8 to 79.8 tokens and from 308.6 to 78.5 tokens respectively compared to Standard RAG while keeping retrieval time comparable.

M+ augments short-term memory θ, long-term memory Θ, a co-trained retriever, and a Multi-LoRA design on top of MemoryLLM’s layer-wise memory pools. On SQuAD-style knowledge retention, M+ maintains accuracy beyond 160k tokens while MemoryLLM-7B collapses before 20k and Llama-3.1-8B-SnapKV fails beyond 30k tokens.

MIRIX organizes Core Memory, Episodic Memory, Semantic Memory, Procedural Memory, Resource Memory, and Knowledge Vault under multi-agent control with Active Retrieval for topic-driven access. On ScreenshotVQA, MIRIX reaches 0.5950 accuracy vs 0.4410 for SigLIP@50 while shrinking storage from 15.07GB to 15.89MB, and on LOCOMO MIRIX scores 85.38% vs 79.09% for Zep.

MMAG organizes conversational memory, long-term user memory, episodic and event-linked memories, sensory and context-aware memory, and short-term working memory under a modular memory controller integrated with Heero’s encrypted Firestore and S3 stores. MMAG delivers a 20% increase in user retention and a 30% increase in average conversation duration on the Heero language learning platform compared to its pre-memory deployment.

Mnemosyne combines a Commitment pipeline with substance and redundancy filters, a probabilistic Recall traversal over a graph-structured store, asynchronous Core Summary updates, and a Pruning module to manage long-term memory on edge devices. On the LoCoMo benchmark, Mnemosyne reaches 60.42% temporal reasoning J-score and a 54.55% overall J-score, compared to 51.55% temporal reasoning and 62.74% overall for Memory-R1, and achieves a 65.8% win rate over a 31.07% naive RAG baseline in human evaluations.

MobileRAG builds a fully on-device RAG stack by integrating EcoVector, Selective Content Reduction, DB Construction, and Chat Application over a local SQLite store. On SQuAD with Qwen2.5 1.5B, MobileRAG reaches 65.1% accuracy while reducing TTFT from 11.78s for Advanced RAG to 7.41s and cutting power from 89.09J to 56.28J.

MR.Rec unifies User-specific Local Memory, Cross-user Global Memory, Reasoning-enhanced Memory Retrieval, and Reinforcement Learning for Memory-synergized Reasoning into a single recommendation assistant pipeline. On the Amazon-C4–based benchmark, MR.Rec achieves NDCG@100 = 0.113 and Recall@100 = 0.270, improving over the best baseline Rec-R1 (NDCG@100 = 0.104, Recall@100 = 0.260).

Muon Outperforms Adam in Tail-End Associative Memory Learning analyzes how VO attention weights, FFN matrices, normalized SVD entropy, and effective rank behave under Muon versus Adam in transformer associative memories. Muon Outperforms Adam in Tail-End Associative Memory Learning finds that applying Muon to VO and FFN nearly recovers full-Muon validation loss (3.5654 vs 3.9242 for All Adam at 10k steps on FineWeb) while improving tail-class accuracy on a heavy-tailed QA task compared to Adam and SGD+Momentum.

PersonaMem-v2 combines PERSONAMEM-V2: IMPLICIT PERSONAS, RL with Long-Context Reasoning, RL with Agentic Memory, and a User Privacy-Aware Design to train Qwen3-4B with GRPO on implicit user preferences from long, noisy histories. PersonaMem-v2 achieves 55.2% MCQ and 60.7% open-ended accuracy on PERSONAMEM-V2, surpassing GPT-5-Chat’s 45.6% and 46.2% while using a 2k-token agentic memory instead of full 32k–128k contexts.