Imprint compresses egocentric observations into interaction patterns via online memory compression, raising QA accuracy from 31.0% to 35.8% while cutting memory 2.3× and latency 11.8× on a seven-day benchmark.
Retrieval-augmented generation with hierarchical knowledge.arXiv preprint arXiv:2503.10150
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 10representative citing papers
DeepRefine refines agent-compiled knowledge bases via multi-turn abductive diagnosis and RL training with a GBD reward, yielding consistent downstream task gains.
HyGRAG is a hierarchical graph RAG framework that constructs LLM summaries over hybrid chunk-entity graphs, retrieves via context and relation awareness across levels, and enables dynamic updates, reporting a 9.7% average accuracy gain on multi-hop reasoning tasks.
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.
SkillRAE organizes skills into a graph and compiles compact, grounded contexts for LLM agents, yielding 11.7% gains on SkillsBench over prior RAE methods.
MemSearch-o1 mitigates memory dilution in agentic LLM search through reasoning-aligned token-level memory growth, retracing with a contribution function, and path reorganization, improving reasoning activation on benchmarks.
AtlasKV integrates billion-scale KGs into LLMs parametrically with sub-linear complexity and low memory by converting triples into key-value representations handled by the model's attention.
Ψ-RAG improves cross-document multi-hop QA performance using an adaptive hierarchical abstract tree and agent-powered hybrid retrieval, outperforming RAPTOR by 25.9% and HippoRAG 2 by 7.4% in average F1.
R²-Searcher introduces fine-grained evidence modeling, retrieval reflection, and R²PO RL to calibrate retrieval-reasoning boundaries and improve multi-hop QA performance.
LLM-driven feature synthesis from data-rich verticals improves MTL ranking models in data-sparse verticals via taxonomic features from user histories.
citing papers explorer
-
Imprint: Online Memory Compression for Long-Horizon Egocentric QA
Imprint compresses egocentric observations into interaction patterns via online memory compression, raising QA accuracy from 31.0% to 35.8% while cutting memory 2.3× and latency 11.8× on a seven-day benchmark.
-
DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning
DeepRefine refines agent-compiled knowledge bases via multi-turn abductive diagnosis and RL training with a GBD reward, yielding consistent downstream task gains.
-
A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation
HyGRAG is a hierarchical graph RAG framework that constructs LLM summaries over hybrid chunk-entity graphs, retrieves via context and relation awareness across levels, and enables dynamic updates, reporting a 9.7% average accuracy gain on multi-hop reasoning tasks.
-
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.
-
SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution
SkillRAE organizes skills into a graph and compiles compact, grounded contexts for LLM agents, yielding 11.7% gains on SkillsBench over prior RAE methods.
-
MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
MemSearch-o1 mitigates memory dilution in agentic LLM search through reasoning-aligned token-level memory growth, retracing with a contribution function, and path reorganization, improving reasoning activation on benchmarks.
-
AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
AtlasKV integrates billion-scale KGs into LLMs parametrically with sub-linear complexity and low memory by converting triples into key-value representations handled by the model's attention.
-
Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation
Ψ-RAG improves cross-document multi-hop QA performance using an adaptive hierarchical abstract tree and agent-powered hybrid retrieval, outperforming RAPTOR by 25.9% and HippoRAG 2 by 7.4% in average F1.
-
R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search
R²-Searcher introduces fine-grained evidence modeling, retrieval reflection, and R²PO RL to calibrate retrieval-reasoning boundaries and improve multi-hop QA performance.
-
Mind the Gap: Bridging Behavioral Silos with LLMs in Multi-Vertical Recommendations
LLM-driven feature synthesis from data-rich verticals improves MTL ranking models in data-sparse verticals via taxonomic features from user histories.