PlanRAG models natural language exploratory reasoning problems as logical query trees, optimizes them via dynamic programming with a multi-dimensional cost model, and executes iterative retrieval-generation over the trees to outperform prior RAG methods on a new dataset.
A survey on knowledge-oriented retrieval-augmented generation
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
NormAct shows MLLMs reach explicit goals in 67.3% of cases but comply with hidden norms in only 26.4%, with NormPerceptor raising task success from 24.2% to 46.7%.
GRACE-RAG is a governed graph-augmented RAG architecture that moves structural reasoning to retrieval, reporting up to 20% quality gains on mid-scale models in closed-domain settings.
A retrieval approach identifies anomalous dimensions in a set of query vectors and retrieves database vectors that are anomalous across those dimensions, with performance improving as query set size grows to around 8.
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
Context-KG uses LLMs to extract user preferences and context from natural language, driving ontology-guided layouts and insights for knowledge graph visualization that improve interpretability and task performance over traditional force-directed methods.
GroupRank uses groupwise LLM reranking with answer-free data synthesis and a group-ranking reward to reach 65.2 NDCG@10 on BRIGHT while providing 6.4x faster inference than listwise baselines.
Hashing-based framework adds DP noise to LSH bucket votes to release private probability distributions for datastores with 2.6% average accuracy loss at epsilon=5.
Large-scale profiling of recent AI literature shows growth in safety, multimodal reasoning, and agent studies alongside stabilization in neural machine translation and graph methods.
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.
citing papers explorer
-
When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problems
PlanRAG models natural language exploratory reasoning problems as logical query trees, optimizes them via dynamic programming with a multi-dimensional cost model, and executes iterative retrieval-generation over the trees to outperform prior RAG methods on a new dataset.
-
NormAct: A Benchmark for Hidden Social Norm Compliance in Embodied Planning
NormAct shows MLLMs reach explicit goals in 67.3% of cases but comply with hidden norms in only 26.4%, with NormPerceptor raising task success from 24.2% to 46.7%.
-
GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings
GRACE-RAG is a governed graph-augmented RAG architecture that moves structural reasoning to retrieval, reporting up to 20% quality gains on mid-scale models in closed-domain settings.
-
Retrieval with Multiple Query Vectors through Anomalous Pattern Detection
A retrieval approach identifies anomalous dimensions in a set of query vectors and retrieves database vectors that are anomalous across those dimensions, with performance improving as query set size grows to around 8.
-
Supervising the search process produces reliable and generalizable information-seeking agents
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
-
Context-KG: Context-Aware Knowledge Graph Visualization with User Preferences and Ontological Guidance
Context-KG uses LLMs to extract user preferences and context from natural language, driving ontology-guided layouts and insights for knowledge graph visualization that improve interpretability and task performance over traditional force-directed methods.
-
GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs
GroupRank uses groupwise LLM reranking with answer-free data synthesis and a group-ranking reward to reach 65.2 NDCG@10 on BRIGHT while providing 6.4x faster inference than listwise baselines.
-
Differentially Private Datastore Generation for Retrieval-Augmented Inference
Hashing-based framework adds DP noise to LSH bucket votes to release private probability distributions for datastores with 2.6% average accuracy loss at epsilon=5.
-
Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval
Large-scale profiling of recent AI literature shows growth in safety, multimodal reasoning, and agent studies alongside stabilization in neural machine translation and graph methods.
-
A Survey of Context Engineering for Large Language Models
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.