MARVEL reaches 37.9 nDCG@10 on the MM-BRIGHT benchmark by combining LLM query expansion, a reasoning-enhanced dense retriever, and GPT-4o CoT reranking, beating prior multimodal encoders by 10.3 points.
hub Canonical reference
Precise zero-shot dense retrieval without relevance labels
Canonical reference. 80% of citing Pith papers cite this work as background.
16
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
roles
background 5representative citing papers
Agentic search over NASA EO-KG yields a 47k-pair benchmark where neural scoring plus LLM reranking raises MRR by over 5x then an additional 28%.
LEVER enables offline composition of pre-trained RL policies via behavioral embeddings and Q-value composition, matching or exceeding training-from-scratch performance in deterministic GridWorld while highlighting limits for long-horizon tasks.
The paper defines a bounded reference architecture for LLM-orchestrated hybrid retrieval in dataset search using BM25, dense embeddings, reciprocal rank fusion, and metadata augmentation with pseudo-queries.
R2MED is the first benchmark for reasoning-driven medical retrieval, where even top models reach only 41.4 nDCG@10 on queries requiring inference beyond lexical or semantic overlap.
Empirical study of RLAIF for portable query generation finds reward shaping controls performance more than optimizer choice and a rule-based reward floor yields +0.147 quality gain.
CICL scores and compresses context evidence for LLM agents via action-shift and outcome-uplift metrics, lifting hit@1 from 0.58 to 0.78 on 50 SWE-bench retrieval tasks.
RGAO combines retrieval-based complexity assessment with a formal budget algebra to enable dynamic topology selection in multi-agent code generation with provable conservation.
LLM-generated reference documents serve as relevance pivots for dynamic ranked-list truncation and adaptive/parallel listwise reranking, reportedly beating prior RLT methods and cutting LLM reranking cost by up to 66%.
BRIDGE reaches 29.7 nDCG@10 on MM-BRIGHT by RL-aligning multimodal queries to text and using a reasoning retriever, beating multimodal encoders and, when combined with Nomic-Vision, exceeding the best text-only retriever at 33.3.
ARK fine-tunes retrievers for answer alignment using KG-augmented curriculum contrastive learning on answer-sufficient positives and progressive hard negatives, reporting 14.5% gains on long-context benchmarks.
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.
Experience-RAG Skill is a reusable agent skill that selects retrieval strategies via experience memory, achieving 0.8924 nDCG@10 on BeIR/nq, hotpotqa, and scifact while outperforming fixed retriever baselines.
LightRAG builds graph structures into RAG indexing and retrieval with dual-level search and incremental updates to improve accuracy and speed.
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
citing papers explorer
-
MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL
MARVEL reaches 37.9 nDCG@10 on the MM-BRIGHT benchmark by combining LLM query expansion, a reasoning-enhanced dense retriever, and GPT-4o CoT reranking, beating prior multimodal encoders by 10.3 points.
-
Bringing Agentic Search to Earth Observation Data Discovery
Agentic search over NASA EO-KG yields a 47k-pair benchmark where neural scoring plus LLM reranking raises MRR by over 5x then an additional 28%.
-
Lever: Inference-Time Policy Reuse under Support Constraints
LEVER enables offline composition of pre-trained RL policies via behavioral embeddings and Q-value composition, matching or exceeding training-from-scratch performance in deterministic GridWorld while highlighting limits for long-horizon tasks.
-
A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search
The paper defines a bounded reference architecture for LLM-orchestrated hybrid retrieval in dataset search using BM25, dense embeddings, reciprocal rank fusion, and metadata augmentation with pseudo-queries.
-
R2MED: A Benchmark for Reasoning-Driven Medical Retrieval
R2MED is the first benchmark for reasoning-driven medical retrieval, where even top models reach only 41.4 nDCG@10 on queries requiring inference beyond lexical or semantic overlap.
-
Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search
Empirical study of RLAIF for portable query generation finds reward shaping controls performance more than optimizer choice and a rule-based reward floor yields +0.147 quality gain.
-
Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents
CICL scores and compresses context evidence for LLM agents via action-shift and outcome-uplift metrics, lifting hit@1 from 0.58 to 0.78 on 50 SWE-bench retrieval tasks.
-
Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation
RGAO combines retrieval-based complexity assessment with a formal budget algebra to enable dynamic topology selection in multi-agent code generation with provable conservation.
-
Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents
LLM-generated reference documents serve as relevance pivots for dynamic ranked-list truncation and adaptive/parallel listwise reranking, reportedly beating prior RLT methods and cutting LLM reranking cost by up to 66%.
-
BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment
BRIDGE reaches 29.7 nDCG@10 on MM-BRIGHT by RL-aligning multimodal queries to text and using a reasoning retriever, beating multimodal encoders and, when combined with Nomic-Vision, exceeding the best text-only retriever at 33.3.
-
ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning
ARK fine-tunes retrievers for answer alignment using KG-augmented curriculum contrastive learning on answer-sufficient positives and progressive hard negatives, reporting 14.5% gains on long-context benchmarks.
-
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.
-
An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration
Experience-RAG Skill is a reusable agent skill that selects retrieval strategies via experience memory, achieving 0.8924 nDCG@10 on BeIR/nq, hotpotqa, and scifact while outperforming fixed retriever baselines.
-
LightRAG: Simple and Fast Retrieval-Augmented Generation
LightRAG builds graph structures into RAG indexing and retrieval with dual-level search and incremental updates to improve accuracy and speed.
-
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.
- FitText: Evolving Agent Tool Ecologies via Memetic Retrieval