ShadowMerge exploits relation-channel conflicts to poison graph-based agent memory, achieving 93.8% average attack success rate on Mem0 and real-world datasets while bypassing existing defenses.
hub Mixed citations
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Mixed citation behavior. Most common role is background (64%).
41
Pith papers citing it
25
external citations · Pith
Background
64% of classified citations
abstract
Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge. However, most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic understanding of the overall document context. We introduce the novel approach of recursively embedding, clustering, and summarizing chunks of text, constructing a tree with differing levels of summarization from the bottom up. At inference time, our RAPTOR model retrieves from this tree, integrating information across lengthy documents at different levels of abstraction. Controlled experiments show that retrieval with recursive summaries offers significant improvements over traditional retrieval-augmented LMs on several tasks. On question-answering tasks that involve complex, multi-step reasoning, we show state-of-the-art results; for example, by coupling RAPTOR retrieval with the use of GPT-4, we can improve the best performance on the QuALITY benchmark by 20% in absolute accuracy.
hub tools
citation-role summary
background 9
baseline 1
method 1
citation-polarity summary
representative citing papers
Storyline trees are hierarchical narrative representations built via top-down and bottom-up inference on scene segments that support adaptive retrieval and outperform baselines on three long-form QA benchmarks.
The paper delivers the first systems characterization of agent memory, with a four-axis taxonomy, phase-aware profiler, evaluation of ten systems on two benchmarks, and ten design recommendations.
OCR-Memory encodes agent trajectories as images with visual anchors and retrieves verbatim text via locate-and-transcribe, yielding gains on long-horizon benchmarks under strict context limits.
Agentic search narrows the gap between dense RAG and GraphRAG but does not remove GraphRAG's advantage on complex multi-hop reasoning.
CLAG organizes agent memory into clusters via an SLM router and uses cluster profiles for two-stage retrieval, yielding better answer quality on QA benchmarks than prior memory systems.
AtomicRAG replaces chunk-based and triple-based GraphRAG with atom-entity graphs that store facts as atomic units and use personalized PageRank plus relevance filtering to achieve higher retrieval accuracy and reasoning robustness on five benchmarks.
KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.
MM-BizRAG applies layout-aware document splitting and decoupled multimodal assembly to raise generative recall on enterprise Q&A tasks by up to 32 points over vision-centric baselines while adding FastRAGEval as a cheaper LLM judge.
HiKEY introduces hierarchical parsing and coarse-to-fine multimodal retrieval to address routing failures and evidence fragmentation in RAG for ODQA, reporting up to 12.9% recall and 6.8% QA gains over baselines.
MemCog introduces a Memory-as-Cognition paradigm with Navigable Memory Store, Cross-Dimensional Navigation Interface, and Proactive Reasoning Protocol, claiming SOTA results on LoCoMo, LongMemEval, and a new ProactiveMemBench.
Goal-Mem decomposes user goals into subgoals for targeted memory retrieval using Natural Language Logic, improving performance on multi-hop reasoning tasks in conversational agents.
ASTRA-QA is a benchmark for abstract document question answering that uses explicit topic sets, unsupported content annotations, and evidence alignments to enable direct scoring of coverage and hallucination.
FT-RAG introduces a fine-grained graph-based retrieval framework for tables plus a new 9870-pair benchmark, reporting 23.5% and 59.2% gains in table- and cell-level hit rates and 62.2% higher exact-value recall over baselines.
MindTrellis enables users and AI to co-create evolving knowledge graphs, outperforming retrieval-only tools in expert-rated content coverage, structural quality, and reduced cognitive load during a study of 12 participants creating slide decks.
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.
GraphRAG-Router uses two-stage reinforcement learning with a cost-aware curriculum reward to route queries across heterogeneous GraphRAGs and LLMs, cutting large-LLM overuse by nearly 30 percent while matching baseline performance on six QA benchmarks.
A unified framework and large-scale comparison of graph-based RAG methods on QA tasks yields new high-performing variants obtained by recombining existing components.
ArchRAG proposes attributed-community hierarchical indexing and LLM clustering to improve accuracy and lower token usage in graph-based retrieval-augmented generation.
GraphRAG improves comprehensiveness and diversity of answers to global questions over million-token document sets by constructing entity graphs and hierarchical community summaries before combining partial responses.
Co-occurrence-aware KB clustering raises session-level RAG coverage from 41% to 58% on WixQA while cutting retrieval calls and compressing the KB to 20% of original size.
CAMI frames multi-index construction for semantic retrieval as a budgeted multi-objective portfolio problem and uses agent-guided search plus confidence-aware pruning to find high-recall configurations with reduced evaluation cost.
A full-paper multimodal knowledge-graph pipeline with a GRPO-trained 4B extractor and tri-source agent CLI reports improved multi-hop scientific reasoning, alongside a released one-million-paper knowledge graph.
Geometry-led weighting outperforms blended memory recall for spatial queries, and a DDA-based visibility predicate correctly flags occluded targets while recall remains occlusion-blind.
citing papers explorer
-
ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
ShadowMerge exploits relation-channel conflicts to poison graph-based agent memory, achieving 93.8% average attack success rate on Mem0 and real-world datasets while bypassing existing defenses.
-
Storyline Trees: Hierarchical Representations for Long-Form Narratives
Storyline trees are hierarchical narrative representations built via top-down and bottom-up inference on scene segments that support adaptive retrieval and outperform baselines on three long-form QA benchmarks.
-
Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
The paper delivers the first systems characterization of agent memory, with a four-axis taxonomy, phase-aware profiler, evaluation of ten systems on two benchmarks, and ten design recommendations.
-
OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory
OCR-Memory encodes agent trajectories as images with visual anchors and retrieves verbatim text via locate-and-transcribe, yielding gains on long-horizon benchmarks under strict context limits.
-
Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems
Agentic search narrows the gap between dense RAG and GraphRAG but does not remove GraphRAG's advantage on complex multi-hop reasoning.
-
CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents
CLAG organizes agent memory into clusters via an SLM router and uses cluster profiles for two-stage retrieval, yielding better answer quality on QA benchmarks than prior memory systems.
-
AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation
AtomicRAG replaces chunk-based and triple-based GraphRAG with atom-entity graphs that store facts as atomic units and use personalized PageRank plus relevance filtering to achieve higher retrieval accuracy and reasoning robustness on five benchmarks.
-
What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.
-
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A
MM-BizRAG applies layout-aware document splitting and decoupled multimodal assembly to raise generative recall on enterprise Q&A tasks by up to 32 points over vision-centric baselines while adding FastRAGEval as a cheaper LLM judge.
-
HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering
HiKEY introduces hierarchical parsing and coarse-to-fine multimodal retrieval to address routing failures and evidence fragmentation in RAG for ODQA, reporting up to 12.9% recall and 6.8% QA gains over baselines.
-
MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents
MemCog introduces a Memory-as-Cognition paradigm with Navigable Memory Store, Cross-Dimensional Navigation Interface, and Proactive Reasoning Protocol, claiming SOTA results on LoCoMo, LongMemEval, and a new ProactiveMemBench.
-
Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems
Goal-Mem decomposes user goals into subgoals for targeted memory retrieval using Natural Language Logic, improving performance on multi-hop reasoning tasks in conversational agents.
-
ASTRA-QA: A Benchmark for Abstract Question Answering over Documents
ASTRA-QA is a benchmark for abstract document question answering that uses explicit topic sets, unsupported content annotations, and evidence alignments to enable direct scoring of coverage and hallucination.
-
FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning
FT-RAG introduces a fine-grained graph-based retrieval framework for tables plus a new 9870-pair benchmark, reporting 23.5% and 59.2% gains in table- and cell-level hit rates and 62.2% higher exact-value recall over baselines.
-
MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Exploration
MindTrellis enables users and AI to co-create evolving knowledge graphs, outperforming retrieval-only tools in expert-rated content coverage, structural quality, and reduced cognitive load during a study of 12 participants creating slide decks.
-
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.
-
GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning
GraphRAG-Router uses two-stage reinforcement learning with a cost-aware curriculum reward to route queries across heterogeneous GraphRAGs and LLMs, cutting large-LLM overuse by nearly 30 percent while matching baseline performance on six QA benchmarks.
-
In-depth Analysis of Graph-based RAG in a Unified Framework
A unified framework and large-scale comparison of graph-based RAG methods on QA tasks yields new high-performing variants obtained by recombining existing components.
-
ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
ArchRAG proposes attributed-community hierarchical indexing and LLM clustering to improve accuracy and lower token usage in graph-based retrieval-augmented generation.
-
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
GraphRAG improves comprehensiveness and diversity of answers to global questions over million-token document sets by constructing entity graphs and hierarchical community summaries before combining partial responses.
-
One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG
Co-occurrence-aware KB clustering raises session-level RAG coverage from 41% to 58% on WixQA while cutting retrieval calls and compressing the KB to 20% of original size.
-
CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval
CAMI frames multi-index construction for semantic retrieval as a budgeted multi-objective portfolio problem and uses agent-guided search plus confidence-aware pruning to find high-recall configurations with reduced evaluation cost.
-
Agents-K1: Towards Agent-native Knowledge Orchestration
A full-paper multimodal knowledge-graph pipeline with a GRPO-trained 4B extractor and tri-source agent CLI reports improved multi-hop scientific reasoning, alongside a released one-million-paper knowledge graph.
-
What Spatial Memory Must Store: Occlusion as the Test for Language-Agent Memory
Geometry-led weighting outperforms blended memory recall for spatial queries, and a DDA-based visibility predicate correctly flags occluded targets while recall remains occlusion-blind.
-
Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
SegTreeMem organizes agent conversation history as a temporally ordered segment tree and shows improved answer quality on long-horizon benchmarks when chronological order is preserved during insertion and retrieval.
-
CALMem : Application-Layer Dual Memory for Conversational AI
CALMem delivers virtually unbounded effective context for LLM conversations via an application-layer dual memory architecture with intra-session retrieval and token-adaptive injection.
-
How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study
Function-based chunking underperforms other strategies in RAG code completion by 3.57-5.64 points, with context length as the dominant factor.
-
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.
-
Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning
A stateful iterative RAG system converts retrieved documents into scored reasoning units, maintains supportive and non-supportive evidence, and performs deficiency-driven query refinement to achieve more robust QA performance.
-
UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough
A new RAG method that retrieves chunks through aggregated entity descriptions performs on par with or slightly better than plain vector RAG, and both beat Microsoft's GraphRAG on three QA benchmarks.
-
TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
TiMem introduces a Temporal Memory Tree that consolidates conversational history into hierarchical persona representations, reaching 75.30% on LoCoMo and 76.88% on LongMemEval-S while cutting recalled length by 52%.
-
ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning
ARK fine-tunes retrievers for answer alignment using KG-augmented curriculum contrastive learning on answer-sufficient positives and progressive hard negatives, reporting 14.5% gains on long-context benchmarks.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
VArify: A Visual Analytics System for Verifying Knowledge Enhanced Large Language Model Responses in Food Science
VArify introduces a tree visualization to support human verification of GraphRAG evidence for LLM responses in food science, evaluated in a study with six domain experts.
-
Chunking German Legal Code
Section and subsection chunking achieves highest recall on legal QA while complex methods like RAPTOR and contextual chunking perform worse and cost more.
-
An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration
Experience-RAG Skill is a reusable agent skill that selects retrieval strategies via experience memory, achieving 0.8924 nDCG@10 on BeIR/nq, hotpotqa, and scifact while outperforming fixed retriever baselines.
-
MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
MemORAI introduces selective memory filtering, provenance tracking in a multi-relational graph, and query-adaptive Dynamic Weighted PageRank retrieval, reporting SOTA results on LOCOMO and LongMemEval for memory retrieval and personalized responses.
-
Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering
Entity-based chunk filtering reduces RAG vector index size by 25-36% with retrieval quality near baseline levels.
-
PDF Retrieval Augmented Question Answering
Develops a multimodal RAG QA system for PDFs by processing non-textual elements and fine-tuning LLMs to handle complex queries combining multiple data types.
-
Retrieval-Augmented Generation for Large Language Models: A Survey
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
- Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework