MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
hub Canonical reference
Zep: A Temporal Knowledge Graph Architecture for Agent Memory
Canonical reference. 88% of citing Pith papers cite this work as background.
64
Pith papers citing it
Background
88% of classified citations
abstract
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark. Additionally, Zep excels in more comprehensive and challenging evaluations than DMR that better reflect real-world enterprise use cases. While existing retrieval-augmented generation (RAG) frameworks for large language model (LLM)-based agents are limited to static document retrieval, enterprise applications demand dynamic knowledge integration from diverse sources including ongoing conversations and business data. Zep addresses this fundamental limitation through its core component Graphiti -- a temporally-aware knowledge graph engine that dynamically synthesizes both unstructured conversational data and structured business data while maintaining historical relationships. In the DMR benchmark, which the MemGPT team established as their primary evaluation metric, Zep demonstrates superior performance (94.8% vs 93.4%). Beyond DMR, Zep's capabilities are further validated through the more challenging LongMemEval benchmark, which better reflects enterprise use cases through complex temporal reasoning tasks. In this evaluation, Zep achieves substantial results with accuracy improvements of up to 18.5% while simultaneously reducing response latency by 90% compared to baseline implementations. These results are particularly pronounced in enterprise-critical tasks such as cross-session information synthesis and long-term context maintenance, demonstrating Zep's effectiveness for deployment in real-world applications.
hub tools
citation-role summary
background 14
baseline 2
citation-polarity summary
claims ledger
- abstract We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark. Additionally, Zep excels in more comprehensive and challenging evaluations than DMR that better reflect real-world enterprise use cases. While existing retrieval-augmented generation (RAG) frameworks for large language model (LLM)-based agents are limited to static document retrieval, enterprise applications demand dynamic knowledge integration from diverse sources including ongoing conversations and business data. Zep addresse
co-cited works
representative citing papers
MemPoison enables stealthy memory poisoning in LLM agents via dialogue by using semantic relational bridges, entity masquerading, and joint embedding optimization to bypass selective extraction and rewriting, achieving up to 0.95 attack success rate.
A Behavioral Specification interpretive layer improves representational accuracy for AI personalization by compressing user data into patterns, outperforming raw corpora and commercial memory systems on held-out behavioral predictions across 14 autobiographical corpora while reducing context cost.
ClawForge is a generator framework that creates reproducible executable benchmarks for command-line agents under state conflict, with ClawForge-Bench showing frontier models reach at most 45.3% strict accuracy and that state inspection drives most performance gaps.
All tested LLM memory systems fail at dependency reasoning in multi-entity evolving scenarios, with only an expensive file-based setup showing partial recovery.
Memory for long-horizon agents should preserve distinctions that affect decisions under a fixed budget, not descriptive features, yielding an exact forgetting boundary and a new online learner DeMem with regret guarantees.
DeepRefine refines agent-compiled knowledge bases via multi-turn abductive diagnosis and RL training with a GBD reward, yielding consistent downstream task gains.
Nautilus Compass is a black-box drift detector for production LLM agents that uses weighted cosine similarity on BGE-m3 embeddings of raw text against anchors, achieving 0.83 ROC AUC on real session traces while shipping as plugins and servers with an audit log.
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
MemoRepair formalizes the cascade update problem in agentic memory and solves it via a min-cut reduction that eliminates invalidated memory exposure to 0% while recovering 91-94% of valid successors at 57-76% of baseline repair cost.
BeliefMem is a probabilistic memory architecture for LLM agents that retains multiple candidate conclusions with probabilities updated by Noisy-OR, achieving superior average performance over deterministic baselines on LoCoMo and ALFWorld.
MemFlow routes queries by intent to tiered memory operations, nearly doubling accuracy of a 1.7B SLM on long-horizon benchmarks compared to full-context baselines.
MemCoE learns memory organization guidelines via contrastive feedback and then trains a guideline-aligned RL policy for memory updates, yielding consistent gains on personalization benchmarks.
vstash shows that hybrid retrieval disagreements provide a free training signal to fine-tune 33M-parameter embeddings, yielding NDCG@10 gains up to 19.5% on NFCorpus and matching some larger models on three of five BEIR datasets.
SAGER equips LLM recommendation agents with per-user evolving policy skills via two-representation architecture, contrastive CoT diagnosis, and skill-augmented listwise reasoning, yielding SOTA gains orthogonal to memory accumulation.
AgenticSZZ reframes bug-inducing commit identification as temporal knowledge graph search navigated by an LLM agent, reporting F1 scores of 0.47-0.79 and up to 34% improvement over prior SZZ methods on three datasets.
MemSearcher trains LLMs to manage compact memory in multi-turn searches via multi-context GRPO for end-to-end RL, outperforming ReAct-style baselines with stable token counts.
MIRIX introduces a modular multi-agent architecture with Core, Episodic, Semantic, Procedural, Resource, and Knowledge Vault memories that outperforms RAG baselines by 35% on ScreenshotVQA and reaches 85.4% on LOCOMO.
MemoryAgentBench is a new multi-turn benchmark assessing four memory competencies in LLM agents—accurate retrieval, test-time learning, long-range understanding, and selective forgetting—showing that existing methods fall short.
MRAgent combines a Cue-Tag-Content associative graph with active reconstruction to enable dynamic memory access in LLM agents, reporting up to 23% gains on long-memory benchmarks with lower token costs.
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
MemGuard assigns functional roles to memories at write time and selectively retrieves only compatible types, reducing heterogeneous contamination and improving reliability by up to 28.27% with 5.8x fewer tokens.
Controlled study shows mixed training curricula improve aggregate F1 on memory QA benchmarks while out-of-domain data transfers targeted skills like temporal reasoning, with per-question-type effects exceeding aggregate differences.
ActiveGraph inverts traditional agent frameworks by treating the append-only event log as the primary source of truth, from which the reactive graph is projected, yielding deterministic replay, forking, and lineage tracking.
citing papers explorer
-
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
-
Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
MemPoison enables stealthy memory poisoning in LLM agents via dialogue by using semantic relational bridges, entity masquerading, and joint embedding optimization to bypass selective extraction and rewriting, achieving up to 0.95 attack success rate.
-
Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization
A Behavioral Specification interpretive layer improves representational accuracy for AI personalization by compressing user data into patterns, outperforming raw corpora and commercial memory systems on held-out behavioral predictions across 14 autobiographical corpora while reducing context cost.
-
ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents
ClawForge is a generator framework that creates reproducible executable benchmarks for command-line agents under state conflict, with ClawForge-Bench showing frontier models reach at most 45.3% strict accuracy and that state inspection drives most performance gaps.
-
MEME: Multi-entity & Evolving Memory Evaluation
All tested LLM memory systems fail at dependency reasoning in multi-entity evolving scenarios, with only an expensive file-based setup showing partial recovery.
-
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
Memory for long-horizon agents should preserve distinctions that affect decisions under a fixed budget, not descriptive features, yielding an exact forgetting boundary and a new online learner DeMem with regret guarantees.
-
DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning
DeepRefine refines agent-compiled knowledge bases via multi-turn abductive diagnosis and RL training with a GBD reward, yielding consistent downstream task gains.
-
Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents
Nautilus Compass is a black-box drift detector for production LLM agents that uses weighted cosine similarity on BGE-m3 embeddings of raw text against anchors, achieving 0.83 ROC AUC on real session traces while shipping as plugins and servers with an audit log.
-
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
-
MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory
MemoRepair formalizes the cascade update problem in agentic memory and solves it via a min-cut reduction that eliminates invalidated memory exposure to 0% while recovering 91-94% of valid successors at 57-76% of baseline repair cost.
-
Belief Memory: Agent Memory Under Partial Observability
BeliefMem is a probabilistic memory architecture for LLM agents that retains multiple candidate conclusions with probabilities updated by Noisy-OR, achieving superior average performance over deterministic baselines on LoCoMo and ALFWorld.
-
MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents
MemFlow routes queries by intent to tiered memory operations, nearly doubling accuracy of a 1.7B SLM on long-horizon benchmarks compared to full-context baselines.
-
Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
MemCoE learns memory organization guidelines via contrastive feedback and then trains a guideline-aligned RL policy for memory updates, yielding consistent gains on personalization benchmarks.
-
vstash: Local-First Hybrid Retrieval with Adaptive Fusion for LLM Agents
vstash shows that hybrid retrieval disagreements provide a free training signal to fine-tune 33M-parameter embeddings, yielding NDCG@10 gains up to 19.5% on NFCorpus and matching some larger models on three of five BEIR datasets.
-
SAGER: Self-Evolving User Policy Skills for Recommendation Agent
SAGER equips LLM recommendation agents with per-user evolving policy skills via two-representation architecture, contrastive CoT diagnosis, and skill-augmented listwise reasoning, yielding SOTA gains orthogonal to memory accumulation.
-
AgenticSZZ: Temporal Knowledge Graph-Guided Agentic Bug-Inducing Commit Identification
AgenticSZZ reframes bug-inducing commit identification as temporal knowledge graph search navigated by an LLM agent, reporting F1 scores of 0.47-0.79 and up to 34% improvement over prior SZZ methods on three datasets.
-
MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
MemSearcher trains LLMs to manage compact memory in multi-turn searches via multi-context GRPO for end-to-end RL, outperforming ReAct-style baselines with stable token counts.
-
MIRIX: Multi-Agent Memory System for LLM-Based Agents
MIRIX introduces a modular multi-agent architecture with Core, Episodic, Semantic, Procedural, Resource, and Knowledge Vault memories that outperforms RAG baselines by 35% on ScreenshotVQA and reaches 85.4% on LOCOMO.
-
Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
MemoryAgentBench is a new multi-turn benchmark assessing four memory competencies in LLM agents—accurate retrieval, test-time learning, long-range understanding, and selective forgetting—showing that existing methods fall short.
-
Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
MRAgent combines a Cue-Tag-Content associative graph with active reconstruction to enable dynamic memory access in LLM agents, reporting up to 23% gains on long-memory benchmarks with lower token costs.
-
Rethinking Memory as Continuously Evolving Connectivity
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
-
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
MemGuard assigns functional roles to memories at write time and selectively retrieves only compatible types, reducing heterogeneous contamination and improving reliability by up to 28.27% with 5.8x fewer tokens.
-
What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QA
Controlled study shows mixed training curricula improve aggregate F1 on memory QA benchmarks while out-of-domain data transfers targeted skills like temporal reasoning, with per-question-type effects exceeding aggregate differences.
-
The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems
ActiveGraph inverts traditional agent frameworks by treating the append-only event log as the primary source of truth, from which the reactive graph is projected, yielding deterministic replay, forking, and lineage tracking.
-
H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure
H-Mem introduces a hybrid tree-plus-graph memory mechanism that evolves short-term agent memories into long-term summaries and enables efficient retrieval, reporting state-of-the-art QA results on three benchmarks.
-
Agentic Recommender System with Hierarchical Belief-State Memory
MARS uses hierarchical event-preference-profile memory with an LLM-scheduled lifecycle of six operations to achieve state-of-the-art results on InstructRec benchmarks.
-
Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
A hybrid LLM-symbolic verifier maintains a dependency graph over conversation turns classified into eight formal update operations, enabling linear-time groundedness checks and precise retraction propagation with a conflict-free guarantee.
-
PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
PAI-2 improves factual correctness in LLM answers by 4% on average across benchmarks using adaptive graph traversal and planning, with 6% gains from traversal algorithms and 18% from enabled planning.
-
PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents
PRISM is a new inference-time retrieval system that achieves higher accuracy than baselines on long-horizon agent tasks while using an order of magnitude less context by combining hierarchical graph search, intent-based costing, compression, and adaptive routing over structured memory.
-
SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
SAGE is a self-evolving agentic graph-memory engine that dynamically constructs and refines structured memory graphs via writer-reader feedback, yielding performance gains on multi-hop QA, open-domain retrieval, and long-term agent benchmarks.
-
ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV
Intent-aware retrieval over assertion-labeled knowledge graphs improves clinical QA accuracy by 22 percentage points on a new MIMIC-IV benchmark that stresses negation, temporality, and attribution.
-
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
-
GASim: A Graph-Accelerated Hybrid Framework for Social Simulation
GASim accelerates hybrid LLM-ABM social simulations via graph-optimized memory, graph message passing, and entropy-driven agent grouping, delivering 9.94x speedup and under 20% token use while aligning with real-world trends.
-
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
-
Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
Memanto delivers 89.8% and 87.1% accuracy on LongMemEval and LoCoMo benchmarks using typed semantic memory and information-theoretic retrieval, outperforming hybrid graph and vector systems with a single query and zero ingestion cost.
-
MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
MemSearch-o1 mitigates memory dilution in agentic LLM search through reasoning-aligned token-level memory growth, retracing with a contribution function, and path reorganization, improving reasoning activation on benchmarks.
-
GAM: Hierarchical Graph-based Agentic Memory for LLM Agents
GAM decouples event-level memory encoding from topic-level consolidation in LLM agents using hierarchical graphs to reduce interference and improve long-term coherence and retrieval.
-
TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
TSUBASA improves long-horizon personalization in LLMs via dynamic memory evolution for writing and context-distillation self-learning for reading, outperforming Mem0 and Memory-R1 on Qwen-3 benchmarks while reducing token use.
-
MemReader: From Passive to Active Extraction for Long-Term Agent Memory
MemReader uses distilled passive and GRPO-trained active extractors to selectively write low-noise long-term memories, outperforming passive baselines on knowledge updating, temporal reasoning, and hallucination tasks.
-
Task-Adaptive Retrieval over Agentic Multi-Modal Web Histories via Learned Graph Memory
ACGM learns task-adaptive sparse graphs over multi-modal agent histories via policy-gradient optimization, reaching 82.7 nDCG@10 and 89.2% Precision@10 on WebShop, VisualWebArena, and Mind2Web while outperforming 19 baselines.
-
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
HingeMem segments dialogue memory via boundary-triggered hyperedges over four elements and applies query-adaptive retrieval, yielding ~20% relative gains and 68% lower QA token cost versus baselines on LOCOMO.
-
FileGram: Grounding Agent Personalization in File-System Behavioral Traces
FileGram grounds AI agent personalization in file-system behavioral traces via a data simulation engine, a diagnostic benchmark, and a bottom-up memory architecture.
-
Opal: Private Memory for Personal AI
Opal enables private long-term memory for personal AI by decoupling reasoning to a trusted enclave with a lightweight knowledge graph and piggybacking reindexing on ORAM accesses.
-
Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
A unified framework for LLM agent memory is benchmarked, with a new hybrid method outperforming state-of-the-art on standard tasks.
-
HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling
HyMem introduces dual-granular memory storage with a lightweight summary module for fast responses and selective activation of a deep LLM module for complex queries, outperforming full-context baselines by 92.6% lower computational cost on LOCOMO and LongMemEval benchmarks.
-
Memory in the Age of AI Agents
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
-
VikingMem: A Memory Base Management System for Stateful LLM-based Applications
VikingMem implements the Memory Base paradigm via event-centric extraction and entity updates on VikingDB with temporal compression, claiming up to 30% better retrieval effectiveness on long-term memory benchmarks.
-
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
Memory-R2 proposes LoGo-GRPO to fix unfair trajectory comparisons in RL training of memory-augmented LLM agents by combining global end-to-end rewards with local rerollouts from identical memory states.
-
PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning
PyraVid is a hierarchical multimodal memory system that structures long videos into pyramids to improve long-horizon reasoning and evidence aggregation.
-
GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory
GRAVITY adds structured relational, temporal, and thematic memory anchors to conversational LLMs at generation time, delivering 7.5-10.1% average gains in LLM-judge accuracy across five host systems on LongMemEval and LoCoMo.