OASIS organizes streaming video into hierarchical events and retrieves memory on-demand via intent-driven refinement to improve long-horizon accuracy and compositional reasoning with bounded token costs.
hub Mixed citations
Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy
Mixed citation behavior. Most common role is background (67%).
16
Pith papers citing it
5
external citations · external index
Background
67% of classified citations
hub tools
citation-role summary
background 4
baseline 1
dataset 1
citation-polarity summary
representative citing papers
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.
MMSearch-R1 uses reinforcement learning to train multimodal models for on-demand multi-turn internet search with image and text tools, outperforming same-size RAG baselines and matching larger ones while cutting search calls by over 30%.
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
FlowRAG adds a quad-level heterogeneous graph with summary hubs and a frequency-aware flow module to improve semantic recall and explicit multi-hop reasoning over prior GraphRAG methods.
Attribution graphs reveal that RAG failures arise from shallow fragmented evidence flow in LLMs, enabling topology-based detection and targeted interventions that reinforce question-guided routing.
On ChemKGMultiHopQA, iterative retrieval-reasoning outperformed oracle gold-context static RAG for all 11 LLMs tested, with gains up to 25.6 percentage points.
MoRE enables MLLMs to dynamically coordinate heterogeneous retrieval experts via Step-GRPO training, yielding over 7% average gains on open-domain QA benchmarks.
R1-Searcher uses two-stage outcome-based RL to train LLMs to invoke external search systems for better reasoning without process rewards or distillation.
A-MEM is a dynamic memory system for LLM agents that builds and refines an interconnected network of notes with agent-driven linking and evolution, showing performance gains over prior memory methods on six models.
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.
ToRA trains language models on interactive tool-use trajectories with imitation learning and output shaping to integrate reasoning and external tools, yielding 13-19% gains on math datasets and new highs like 44.6% on MATH for a 7B model.
With serial-numbered facts, swapping LLM judgment for direct candidate extraction plus Python max(serial) lifts MAB FactConsolidation to 78/95% single-hop and 30/51% multi-hop, beating all 22 published systems at 262K, but ties LLM judgment on LongMemEval.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
Carolina Guide is a multi-agent RAG system with guardrails that achieves 98.9% retrieval success and 0.89 Safety F1 on a 90-query test set by prioritizing citation enforcement and refusal of unsafe queries over conversational features.
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
citing papers explorer
-
OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
OASIS organizes streaming video into hierarchical events and retrieves memory on-demand via intent-driven refinement to improve long-horizon accuracy and compositional reasoning with bounded token costs.
-
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.
-
MMSearch-R1: Incentivizing LMMs to Search
MMSearch-R1 uses reinforcement learning to train multimodal models for on-demand multi-turn internet search with image and text tools, outperforming same-size RAG baselines and matching larger ones while cutting search calls by over 30%.
-
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
-
FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow
FlowRAG adds a quad-level heterogeneous graph with summary hubs and a frequency-aware flow module to improve semantic recall and explicit multi-hop reasoning over prior GraphRAG methods.
-
Why Retrieval-Augmented Generation Fails: A Graph Perspective
Attribution graphs reveal that RAG failures arise from shallow fragmented evidence flow in LLMs, enabling topology-based detection and targeted interventions that reinforce question-guided routing.
-
When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
On ChemKGMultiHopQA, iterative retrieval-reasoning outperformed oracle gold-context static RAG for all 11 LLMs tested, with gains up to 25.6 percentage points.
-
Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
MoRE enables MLLMs to dynamically coordinate heterogeneous retrieval experts via Step-GRPO training, yielding over 7% average gains on open-domain QA benchmarks.
-
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
R1-Searcher uses two-stage outcome-based RL to train LLMs to invoke external search systems for better reasoning without process rewards or distillation.
-
A-MEM: Agentic Memory for LLM Agents
A-MEM is a dynamic memory system for LLM agents that builds and refines an interconnected network of notes with agent-driven linking and evolution, showing performance gains over prior memory methods on six models.
-
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.
-
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
ToRA trains language models on interactive tool-use trajectories with imitation learning and output shaping to integrate reasoning and external tools, yielding 13-19% gains on math datasets and new highs like 44.6% on MATH for a 7B model.
-
Reliable Post-Retrieval Assembly for Agent Memory: Separating Evidence Extraction from Policy Execution
With serial-numbered facts, swapping LLM judgment for direct candidate extraction plus Python max(serial) lifts MAB FactConsolidation to 78/95% single-hop and 30/51% multi-hop, beating all 22 published systems at 262K, but ties LLM judgment on LongMemEval.
-
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.
-
Carolina Guide: A Multi-Agent RAG System with Institutional Guardrails for Academic Policy Assistance
Carolina Guide is a multi-agent RAG system with guardrails that achieves 98.9% retrieval success and 0.89 Safety F1 on a 90-query test set by prioritizing citation enforcement and refusal of unsafe queries over conversational features.
-
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.