REVIEW 30 cited by
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
In order to thrive in hostile and ever-changing natural environments, mammalian brains evolved to store large amounts of knowledge about the world and continually integrate new information while avoiding catastrophic forgetting. Despite the impressive accomplishments, large language models (LLMs), even with retrieval-augmented generation (RAG), still struggle to efficiently and effectively integrate a large amount of new experiences after pre-training. In this work, we introduce HippoRAG, a novel retrieval framework inspired by the hippocampal indexing theory of human long-term memory to enable deeper and more efficient knowledge integration over new experiences. HippoRAG synergistically orchestrates LLMs, knowledge graphs, and the Personalized PageRank algorithm to mimic the different roles of neocortex and hippocampus in human memory. We compare HippoRAG with existing RAG methods on multi-hop question answering and show that our method outperforms the state-of-the-art methods remarkably, by up to 20%. Single-step retrieval with HippoRAG achieves comparable or better performance than iterative retrieval like IRCoT while being 10-30 times cheaper and 6-13 times faster, and integrating HippoRAG into IRCoT brings further substantial gains. Finally, we show that our method can tackle new types of scenarios that are out of reach of existing methods. Code and data are available at https://github.com/OSU-NLP-Group/HippoRAG.
Forward citations
Cited by 30 Pith papers
-
SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges
SAG represents document chunks as event-entity rows and uses query-time SQL joins over shared entities to activate multi-hop evidence chains, achieving state-of-the-art Recall@5 on three multi-hop QA benchmarks.
-
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
On an enterprise corpus scaled from 1.7M to 601M tokens, BM25 beats raw-file agentic search, dense retrieval, and graph RAG at large sizes, crossing near 10M tokens.
-
When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory
ReFind, an agent-controlled keyword search over raw chat logs, outperforms structured memory systems such as HippoRAG 2 on conversational-memory benchmarks without building any semantic index.
-
DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering
A training-free agentic graph RAG system that navigates document hierarchies and cross-region links, improving answer quality by 7.8% and context sufficiency by 17.7% over the strongest baseline across four CDQA benchmarks.
-
Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings
A ground-truth-first synthetic memory benchmark shows that agent-memory architecture rankings invert with history length: short-horizon leaders lose at nine weeks.
-
Beyond Memory Leaderboards: Evaluating Scientific Memory as Budgeted Context Restoration
Scientific-memory leaderboards are misleading unless retrieval budget and modality are reported; under matched budgets, simple RAG baselines tie with structured memory systems.
-
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.
-
A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory
Explicit bank, retrieval, and QA state roles reduce ghost-memory failures on conflict-heavy LTP and improve some temporal scores on LoCoMo, with host-dependent gains.
-
AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents
A benchmark comparing five memory strategies for conversational agents on three public datasets finds dense vector retrieval alone maintains long-range recall, at roughly 25 times the token cost of recency windows.
-
MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying
MemoCue uses a 5W scenario classifier and Monte Carlo Tree Search to generate cue-rich questions that help LLM agents guide humans through memory recall.
-
BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering
BYOKG-RAG combines LLM-generated entities, paths, queries, and candidate answers with multiple graph retrieval tools to answer questions over custom knowledge graphs without training data.
-
XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation
A visual analytics framework helps GraphRAG developers trace suspicious retrievals through graph construction and LLM invocation stages, with a user study suggesting faster, more accurate failure diagnosis than an exi...
-
A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning
DGAR uses diffusion-generated, model-guided historical entity distributions with adaptive replay to reduce catastrophic forgetting in temporal knowledge graph reasoning.
-
Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking
A nine-task benchmark shows structural knowledge prompting gives LLMs coarse-grained understanding but not fine-grained entity precision, and simple MLP adapters outperform complex ones.
-
Unanswerability Evaluation for Retrieval Augmented Generation
UAEval4RAG synthesizes six categories of unanswerable queries from any knowledge base and evaluates whether RAG systems reject them acceptably.
-
KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?
A new benchmark, KnowShiftQA, shows that retrieval-augmented LLMs drop 22 to 27 points in accuracy when textbook facts are hypothetically updated to conflict with the model's parametric knowledge.
-
SiReRAG: Indexing Similar and Related Information for Multihop Reasoning
SiReRAG indexes a corpus with both a similarity tree and an entity-based relatedness tree, improving average multihop QA F1 by about 1.9 points over prior RAG indexing methods.
-
Mixture-of-PageRanks: Replacing Long-Context with Real-Time, Sparse GraphRAG
A sparse, CPU-only PageRank-based retriever with a query-type router matches or beats long-context LLMs and other RAG methods on several long-context benchmarks.
-
SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents
SuperLocalMemory 4.0 is a local-first, governed memory runtime for AI agents with a verifiable transaction spine, cross-store erasure receipts, and measured control-plane overhead.
-
LatticeMind: A Conflict-Aware Memory Primitive for Multi-Agent Systems
A write-time conflict-aware memory that tracks claim status and reconciles contradictions reaches 0.97 accuracy on a label-blind 75-example conflict benchmark, far above answer-level aggregation baselines.
-
SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents
SodaMem, an evidence-grounded temporal graph memory, reaches 92.8 percent accuracy on LongMemEval-S at about 0.16 cents per question.
-
KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems
KAP compiles structured knowledge priors into runtime access plans that cut proposal-time KV access to 5.5% at 128K while matching full-context QA quality and yielding up to 1.19× decode throughput.
-
GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework
GOSU globally merges semantic units from text chunks into a unit-centric knowledge graph and uses three-tier keyword retrieval to improve RAG generation quality, according to LLM-judge win rates.
-
STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning
A spatio-temporal memory agent combining a textual history summarizer, a spatial knowledge graph, and a planner-critic loop outperforms ReAct, Reflexion, and AdaPlanner on TextWorld cooking tasks.
-
Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents
The authors propose episodic memory, with five defining properties, as the unifying framework needed for LLM agents to learn and remember over long time horizons.
-
M+: Extending MemoryLLM with Scalable Long-Term Memory
M+ adds a co-trained retriever and CPU-stored long-term memory to MemoryLLM, extending tested knowledge retention from under 20k to over 160k tokens at similar GPU memory cost.
-
Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs
Four-axis fusion (dense, BM25, triples, images) over 43 Japanese disaster PDFs claims 0.99 recall and a 71.6% multi-hop gain, but the benchmark labels and fusion weights come from inside the same pipeline.
-
SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration
A human-in-the-loop RAG system that lets users select relevant document blocks and later uses their interaction logs to improve retrieval, with small user studies showing gains over baseline RAG.
-
Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
A review that organizes RAG evaluation into internal and external categories, catalogs dozens of benchmarks, and analyzes evaluation practices in 582 conference papers.
-
An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems
A survey and position paper that reviews LLM prompting, RAG, and RL techniques and argues they could support open-ended implementation generation, without presenting new results.
Discussion (0). Continue with ORCID to comment.