记忆检索

RAG、attention-based、semantic search 等检索机制

共 88 篇论文，自动生成于 2026-05-13

论文列表

• "AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition" — arXiv:"2604.12735"
• "Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents" — arXiv:2604.20572
• "Towards Autonomous Memory Agents" — arXiv:"2602.22406"
• "AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning" — arXiv:2604.17337
• "Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation" — arXiv:2604.11628
• "Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks" — arXiv:2604.11610
• Belief Memory: Agent Memory Under Partial Observability — arXiv:2605.05583
• "CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering" — arXiv:2604.26176
• "CIG: Measuring Conversational Information Gain in Deliberative Dialogues with Semantic Memory Dynamics" — arXiv:2604.15647
• "DeltaMem: RL-Driven Adaptive Memory Management for Long-Context LLM Agents" — arXiv:2604.01560
• "Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving" — arXiv:2604.20183
• "EngramaBench: Evaluating Long-Term Conversational Memory with Structured Graph Retrieval" — arXiv:2604.21229
• EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium — arXiv:2605.09278
• "Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios" — arXiv:2605.06185
• "EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory" — arXiv:2604.27695
• "An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration" — arXiv:2605.03989
• "Explainable Innovation Engine: Dual-Tree Agent-RAG with Methods-as-Nodes and Verifiable Write-Back" — arXiv:2603.09192
• "Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture" — arXiv:2605.01567
• "Architecture Matters More Than Scale: A Comparative Study of Retrieval and Memory Augmentation for Financial QA Under SME Compute Constraints" — arXiv:"2604.17979"
• "Goal-Mem: Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems" — arXiv:2605.12213
• Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems — arXiv:2605.04264
• "GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory" — arXiv:"2605.01688"
• "HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution" — arXiv:"2605.09942"
• "HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues" — arXiv:"2604.06845"
• "HeRo: Adaptive Orchestration of Agentic RAG on Heterogeneous Mobile SoC" — arXiv:2603.01661
• "HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents" — arXiv:2604.18349
• "I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generation" — arXiv:2603.23413
• "Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction" — arXiv:"2604.07659"
• "Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents" — arXiv:"2605.05702"
• "LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG" — arXiv:2605.06285
• "Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents" — arXiv:2604.27283
• "LightMem: Lightweight LLM Agent Memory with Small Language Models" — arXiv:2604.07798
• "LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues" — arXiv:2605.12493
• "MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation" — arXiv:"2604.18509"
• "MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare" — arXiv:2605.11814
• "MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing" — arXiv:2605.02199
• "Memento: Augmenting Personalized Memory via Practical Multimodal Wearable Sensing in Visual Search and Wayfinding Navigation" — arXiv:2504.19772
• "MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents" — arXiv:2605.03312
• "MemLoRA: Distilling Expert Adapters for On-Device Memory Systems" — arXiv:2512.04763
• "MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents" — arXiv:2604.04853
• "From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents" — arXiv:"2604.20006"
• "MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents" — arXiv:2605.01386
• "MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory" — arXiv:2605.07242
• "The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents" — arXiv:2605.08060
• "Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data" — arXiv:2604.20261
• Memory-QA: Answering Recall Questions Based on Multimodal Memories — arXiv:2509.18436
• "MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization" — arXiv:2603.25973
• "Spatial Metaphors for LLM Memory: A Critical Analysis of the MemPalace Architecture" — arXiv:2604.21284
• "MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs" — arXiv:2605.08374
• "MemReader: From Passive to Active Extraction for Long-Term Agent Memory" — arXiv:2604.07877
• MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval — arXiv:2605.06132
• MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading — arXiv:2605.10268
• "MEMRES: A Memory-Augmented Resolver with Confidence Cascade for Agentic Python Dependency Resolution" — arXiv:"2604.16941"
• "MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents" — arXiv:2605.00356
• "MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning" — arXiv:"2603.03379"
• "MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents" — arXiv:2605.03675
• "MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detection" — arXiv:"2604.27934"
• "PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory" — arXiv:"2604.08000"
• "PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments" — arXiv:2603.23231
• "PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents" — arXiv:2605.12260
• "PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents" — arXiv:"2605.08468"
• "RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance" — arXiv:"2604.22217"
• Retrieval-Augmented Memory for Online Learning — arXiv:2512.02333
• "Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory" — arXiv:2604.03588
• "Re:Member: Emotional Question Generation from Personal Memories" — arXiv:2510.19030
• "Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval" — arXiv:2603.09250
• "RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark" — arXiv:2605.10921
• "RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation" — arXiv:2605.07129
• "Response-Aware User Memory Selection for LLM Personalization" — arXiv:2604.14473
• "SelRoute: Query-Type-Aware Routing for Long-Term Conversational Memory Retrieval" — arXiv:2604.02431
• "Semantic Entanglement in Vector-Based Retrieval: A Formal Framework and Context-Conditioned Disentanglement Pipeline for Agentic RAG Systems" — arXiv:2604.17677
• "Emerging Human-like Strategies for Semantic Memory Foraging in Large Language Models" — arXiv:2603.01822
• "Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoning" — arXiv:2504.06135
• "Skill Retrieval Augmentation for Agentic AI" — arXiv:"2604.24594"
• "SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval" — arXiv:"2603.15599"
• "SocializeChat: A GPT-Based AAC Tool Grounded in Personal Memories to Support Social Communication" — arXiv:2510.19017
• "From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling" — arXiv:2604.25847
• "STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?" — arXiv:2605.06527
• "Test-Time Strategies for More Efficient and Accurate Agentic RAG" — arXiv:2603.12396
• "Thought-Retriever: Don't Just Retrieve Raw Data, Retrieve Thoughts for Memory-Augmented Agentic Systems" — arXiv:"2604.12231"
• "Toward Agentic RAG for Ukrainian" — arXiv:2604.14896
• "The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory" — arXiv:"2605.09330"
• "TreeMem: Tree-based Credit Assignment for Multi-Agent Memory System" — arXiv:2605.04811
• "Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall" — arXiv:2605.04897
• "Venus: An Efficient Edge Memory-and-Retrieval System for VLM-based Online Video Understanding" — arXiv:2512.07344
• "VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph" — arXiv:2602.12735
• "When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory" — arXiv:2605.07313
• WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning — arXiv:2512.02425