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 Mixed citations
Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
Mixed citation behavior. Most common role is background (57%).
24
Pith papers citing it
Background
57% of classified citations
abstract
Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component-memory, encompassing how agents memorize, update, and retrieve long-term information-is under-evaluated due to the lack of benchmarks. We term agents with memory mechanisms as memory agents. In this paper, based on classic theories from memory science and cognitive science, we identify four core competencies essential for memory agents: accurate retrieval, test-time learning, long-range understanding, and selective forgetting. Existing benchmarks either rely on limited context lengths or are tailored for static, long-context settings like book-based QA, which do not reflect the interactive, multi-turn nature of memory agents that incrementally accumulate information. Moreover, no existing benchmarks cover all four competencies. We introduce MemoryAgentBench, a new benchmark specifically designed for memory agents. Our benchmark transforms existing long-context datasets and incorporates newly constructed datasets into a multi-turn format, effectively simulating the incremental information processing characteristic of memory agents. By carefully selecting and curating datasets, our benchmark provides comprehensive coverage of the four core memory competencies outlined above, thereby offering a systematic and challenging testbed for assessing memory quality. We evaluate a diverse set of memory agents, ranging from simple context-based and retrieval-augmented generation (RAG) systems to advanced agents with external memory modules and tool integration. Empirical results reveal that current methods fall short of mastering all four competencies, underscoring the need for further research into comprehensive memory mechanisms for LLM agents.
hub tools
citation-role summary
background 6
baseline 1
citation-polarity summary
representative citing papers
EgoMemReason is a new benchmark showing that even the best multimodal models achieve only 39.6% accuracy on reasoning tasks that require integrating sparse evidence across days in egocentric video.
MemConflict provides a benchmark for testing LLM long-term memory systems under dynamic, static, and conditional conflicts involving temporal validity, factual correctness, and contextual applicability.
MemGym unifies agent gyms into a memory benchmark with isolated scoring across tool-use, research, coding, and computer-use regimes plus a lightweight reward model for tractable coding evaluation.
The paper presents ChildAgentEval as the first psychometrically grounded benchmark comparing MLLM-based agents' reasoning performance to age-specific human cognitive stages.
SMMBench is a benchmark evaluating multimodal agents on cross-source reasoning, conflict resolution, preference reasoning, and action prediction, showing current systems struggle with evidence distributed across heterogeneous sources.
GroupMemBench is a new benchmark exposing that LLM agent memory systems fail on group conversation properties like speaker-grounded tracking and audience-adapted responses, with top systems at 46% accuracy.
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
A new evaluation protocol shows agent memory reliability degrades variably with added irrelevant sessions depending on agent, memory interface, and scale.
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.
Long-horizon enterprise AI agents' decisions decompose into four measurable axes, with benchmark experiments on six memory architectures revealing distinct weaknesses and reversing a pre-registered prediction on summarization.
Memory Worth converges almost surely to the conditional probability of task success given memory retrieval and correlates at rho=0.89 with ground-truth utility in controlled experiments.
EvoMemBench evaluates 15 memory methods for LLM agents and finds long-context baselines competitive with no single memory approach working consistently across settings.
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
δ-mem augments frozen LLMs with an 8x8 online memory state updated by delta-rule learning to generate low-rank attention corrections, delivering 1.10x average gains over the backbone and larger improvements on memory-heavy tasks.
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.
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 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.
Deterministic Projection Memory (DPM) delivers stateless, deterministic decision memory for enterprise AI agents that matches or exceeds summarization-based approaches at tight memory budgets while improving speed, determinism, and auditability.
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 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.
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
Execution lineage models AI-native work as a DAG of computations with explicit dependencies, achieving perfect state preservation in controlled update tasks where loop-based agents introduce churn and contamination.
NEMORI is an adaptive memory distillation framework for LLM agents that transforms raw interactions into narratives and extracts insights via prediction error to decide what deserves retention.
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.
-
EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding
EgoMemReason is a new benchmark showing that even the best multimodal models achieve only 39.6% accuracy on reasoning tasks that require integrating sparse evidence across days in egocentric video.
-
MemConflict: Evaluating Long-Term Memory Systems Under Memory Conflicts
MemConflict provides a benchmark for testing LLM long-term memory systems under dynamic, static, and conditional conflicts involving temporal validity, factual correctness, and contextual applicability.
-
MemGym: a Long-Horizon Memory Environment for LLM Agents
MemGym unifies agent gyms into a memory benchmark with isolated scoring across tool-use, research, coding, and computer-use regimes plus a lightweight reward model for tractable coding evaluation.
-
Evaluating Cognitive Age Alignment in Interactive AI Agents
The paper presents ChildAgentEval as the first psychometrically grounded benchmark comparing MLLM-based agents' reasoning performance to age-specific human cognitive stages.
-
SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
SMMBench is a benchmark evaluating multimodal agents on cross-source reasoning, conflict resolution, preference reasoning, and action prediction, showing current systems struggle with evidence distributed across heterogeneous sources.
-
GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
GroupMemBench is a new benchmark exposing that LLM agent memory systems fail on group conversation properties like speaker-grounded tracking and audience-adapted responses, with top systems at 46% accuracy.
-
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
-
When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
A new evaluation protocol shows agent memory reliability degrades variably with added irrelevant sessions depending on agent, memory interface, and scale.
-
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.
-
Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents
Long-horizon enterprise AI agents' decisions decompose into four measurable axes, with benchmark experiments on six memory architectures revealing distinct weaknesses and reversing a pre-registered prediction on summarization.
-
When to Forget: A Memory Governance Primitive
Memory Worth converges almost surely to the conditional probability of task success given memory retrieval and correlates at rho=0.89 with ground-truth utility in controlled experiments.
-
EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
EvoMemBench evaluates 15 memory methods for LLM agents and finds long-context baselines competitive with no single memory approach working consistently across settings.
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
-
$\delta$-mem: Efficient Online Memory for Large Language Models
δ-mem augments frozen LLMs with an 8x8 online memory state updated by delta-rule learning to generate low-rank attention corrections, delivering 1.10x average gains over the backbone and larger improvements on memory-heavy tasks.
-
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.
-
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.
-
Stateless Decision Memory for Enterprise AI Agents
Deterministic Projection Memory (DPM) delivers stateless, deterministic decision memory for enterprise AI agents that matches or exceeds summarization-based approaches at tight memory budgets while improving speed, determinism, and auditability.
-
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.
-
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
-
From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work
Execution lineage models AI-native work as a DAG of computations with explicit dependencies, achieving perfect state preservation in controlled update tasks where loop-based agents introduce churn and contamination.
-
What Deserves Memory: Adaptive Memory Distillation for LLM Agents
NEMORI is an adaptive memory distillation framework for LLM agents that transforms raw interactions into narratives and extracts insights via prediction error to decide what deserves retention.