GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG
Retrieval-Augmented Generation (RAG) systems increasingly employ multiple LLM agents. Yet, most prior work optimizes components in isolation rather than coordinating improvements across the pipeline. We introduce GRADRAG, a framework for cross-component prompt adaptation that models the RAG pipeline as a computational graph and propagates structured evaluation feedback to update upstream agents. An Evaluator critiques downstream answers and supporting evidence, producing actionable feedback that a Prompt Optimizer uses to iteratively update adaptive agents, such as retrievers, graph constructo
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “GRADRAG: Cross-Component Prompt Adaptation for Coordinated M” ≈ “AgentCore-8B””
- PossiblePossibly related (embedding) · 26%microsoft/graphrag →
“Possibly related via embedding similarity 0.56 (not asserted). Timestamp check: artifact slightly before paper (-6d).”
- FuzzySimilar title/name (fuzzy) · 87%SWE-agent/SWE-agent →
“Fuzzy title match (0.94): “GRADRAG: Cross-Component Prompt Adaptation for Coordinated M” ≈ “SWE-agent/SWE-agent””
- FuzzySimilar title/name (fuzzy) · 87%zhayujie/CowAgent →
“Fuzzy title match (0.94): “GRADRAG: Cross-Component Prompt Adaptation for Coordinated M” ≈ “zhayujie/CowAgent””
- FuzzySimilar title/name (fuzzy) · 66%open-multi-agent/open-multi-agent →
“Fuzzy title match (0.78): “GRADRAG: Cross-Component Prompt Adaptation for Coordinated M” ≈ “open-multi-agent/open-multi-agent””
- FuzzySimilar title/name (fuzzy) · 59%NousResearch/hermes-agent →
“Fuzzy title match (0.73): “GRADRAG: Cross-Component Prompt Adaptation for Coordinated M” ≈ “NousResearch/hermes-agent””
- FuzzySimilar title/name (fuzzy) · 59%bojieli/ai-agent-book →
“Fuzzy title match (0.73): “GRADRAG: Cross-Component Prompt Adaptation for Coordinated M” ≈ “bojieli/ai-agent-book””
- LinkedLinked via arxiv author · 85%Paolo Pedinotti →
“GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG”