CQC-RAG improves RAG factuality by generating diverse equivalent queries, building query-specific contexts, and selecting answers via cross-query confidence stability, with reported gains of +4.76 pp EM on TriviaQA and +9.12 pp EM on MuSiQue.
Dmqr-rag: Diverse multi-query rewriting for rag
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 7roles
background 2representative citing papers
BLAgent achieves over 78% top-1 file-level bug localization accuracy on SWE-bench-Lite with open-source models and over 86% with closed-source models while being over 18x cheaper than the strongest baseline.
Agents that evolve pseudo-tool search descriptions during execution reach an 84.3% StableToolBench pass rate, +26.7 points over static query retrieval, with gains growing with base-model capability.
OASES co-trains a search policy and an outcome-aligned state evaluator so intermediate search steps get denser, outcome-consistent process rewards and beat strong RL baselines on multi-hop QA.
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.
CoveR improves nugget coverage by 10% over dense baselines in long-form RAG via coverage-aware contrastive training on LLM-generated sub-question signals without losing relevance performance.
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
citing papers explorer
-
CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency
CQC-RAG improves RAG factuality by generating diverse equivalent queries, building query-specific contexts, and selecting answers via cross-query confidence stability, with reported gains of +4.76 pp EM on TriviaQA and +9.12 pp EM on MuSiQue.
-
BLAgent: Agentic RAG for File-Level Bug Localization
BLAgent achieves over 78% top-1 file-level bug localization accuracy on SWE-bench-Lite with open-source models and over 86% with closed-source models while being over 18x cheaper than the strongest baseline.
-
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval
Agents that evolve pseudo-tool search descriptions during execution reach an 84.3% StableToolBench pass rate, +26.7 points over static query retrieval, with gains growing with base-model capability.
-
OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
OASES co-trains a search policy and an outcome-aligned state evaluator so intermediate search steps get denser, outcome-consistent process rewards and beat strong RL baselines on multi-hop QA.
-
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.
-
Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability
CoveR improves nugget coverage by 10% over dense baselines in long-form RAG via coverage-aware contrastive training on LLM-generated sub-question signals without losing relevance performance.
-
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.