A new evaluation protocol shows agent memory reliability degrades variably with added irrelevant sessions depending on agent, memory interface, and scale.
arXiv preprint arXiv:2510.10114 , year=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 11roles
background 2polarities
background 2representative citing papers
Agentic search narrows the gap between dense RAG and GraphRAG but does not remove GraphRAG's advantage on complex multi-hop reasoning.
EviProp improves evidence-page retrieval in long multimodal documents by combining dense visual priors with sparse chunk seeds and running Personalized PageRank on a multimodal Chunk-Page graph.
MemGraphRAG uses a memory-based multi-agent system for globally consistent graph construction from fragmented corpora plus a memory-aware hierarchical retriever, claiming better benchmark performance than prior GraphRAG methods at similar cost.
MoG uses hub graphs for shared context and sparsely activates expert graphs with a topology-aware router, reporting over 20% relative gains on MuSiQue.
DualGraph combines semantic textual KGs with symbolic KGs for semi-structured QA and introduces the SpecsQA benchmark, outperforming baselines on both open and specification questions.
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.
A lightweight hierarchical multimodal graph RAG that fuses entity-grounded visual objects with text nodes and propagates relevance via multi-granularity PPR, delivering SOTA multimodal task performance at far lower construction cost.
Proposes LLM-driven logical retrieval in agentic RAG with inverted-index backend, matching hybrid baselines at lower cost and with reduced hallucinations.
Graphs can help LLMs reduce hallucinations, boost reasoning via prompting techniques, and better process structured data.
citing papers explorer
-
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.
-
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.
-
EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval
EviProp improves evidence-page retrieval in long multimodal documents by combining dense visual priors with sparse chunk seeds and running Personalized PageRank on a multimodal Chunk-Page graph.
-
MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation
MemGraphRAG uses a memory-based multi-agent system for globally consistent graph construction from fragmented corpora plus a memory-aware hierarchical retriever, claiming better benchmark performance than prior GraphRAG methods at similar cost.
-
MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation
MoG uses hub graphs for shared context and sparsely activates expert graphs with a topology-aware router, reporting over 20% relative gains on MuSiQue.
-
Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering
DualGraph combines semantic textual KGs with symbolic KGs for semi-structured QA and introduces the SpecsQA benchmark, outperforming baselines on both open and specification questions.
-
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.
-
MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation
A lightweight hierarchical multimodal graph RAG that fuses entity-grounded visual objects with text nodes and propagates relevance via multi-granularity PPR, delivering SOTA multimodal task performance at far lower construction cost.
-
Rethinking Agentic RAG: Toward LLM-Driven Logical Retrieval Beyond Embeddings
Proposes LLM-driven logical retrieval in agentic RAG with inverted-index backend, matching hybrid baselines at lower cost and with reduced hallucinations.
-
Position: How can Graphs Help Large Language Models?
Graphs can help LLMs reduce hallucinations, boost reasoning via prompting techniques, and better process structured data.
- Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering