Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.
L ong LLML ingua: Accelerating and Enhancing LLM s in Long Context Scenarios via Prompt Compression
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
ADEMA is a knowledge-state orchestration architecture for LLM agents that uses explicit epistemic bookkeeping, checkpoint-resumable persistence, and artifact-first assembly to support reliable long-horizon knowledge synthesis.
QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.
Orchestrating one 8B model in three roles at inference time doubles task completion on AppWorld from 5.4% to 8.9%, surpassing a 33B baseline.
citing papers explorer
-
Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks
Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.
-
ADEMA: A Knowledge-State Orchestration Architecture for Long-Horizon Knowledge Synthesis with LLMAgents
ADEMA is a knowledge-state orchestration architecture for LLM agents that uses explicit epistemic bookkeeping, checkpoint-resumable persistence, and artifact-first assembly to support reliable long-horizon knowledge synthesis.
-
Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.
-
Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents
Orchestrating one 8B model in three roles at inference time doubles task completion on AppWorld from 5.4% to 8.9%, surpassing a 33B baseline.