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.
Minirag: Towards extremely simple retrieval-augmented generation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
UniD³ applies KG-RAG with Llama 3.3-70B to build six knowledge graphs and generate large validated datasets for drug-disease matching, effectiveness assessment, and target analysis from biomedical literature.
PPAI proposes prototype-based query-agent scoring and a multi-agent Bayesian game for P2P interoperability among personalized LLM agents on edge devices, claiming up to 7.96% accuracy gain and 16.34% latency reduction.
InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.
citing papers explorer
-
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.
-
UniD$^3$: A Knowledge Graph-Enhanced RAG Framework for Drug-Disease Discovery and Reasoning
UniD³ applies KG-RAG with Llama 3.3-70B to build six knowledge graphs and generate large validated datasets for drug-disease matching, effectiveness assessment, and target analysis from biomedical literature.
-
PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence
PPAI proposes prototype-based query-agent scoring and a multi-agent Bayesian game for P2P interoperability among personalized LLM agents on edge devices, claiming up to 7.96% accuracy gain and 16.34% latency reduction.
-
Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking
InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.