VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval
Large language models are increasingly used in practical systems, making efficient model selection important for reducing deployment cost. LLM routing has emerged as a practical solution for allocating each input query to an appropriate model under a desired cost-performance trade-off. Existing routing methods often estimate model suitability from the surface semantics or embedding similarity of the input query. However, such methods may ignore the underlying difficulty of a query, leading to suboptimal routing decisions. To address the challenge, we propose VDAR-Router, a difficulty-aware ret
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.
- LinkedLinked via arxiv author · 85%Yu-Chien Tang →
“VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval”
- LinkedLinked via arxiv author · 85%Jun-Chen Hung →
“VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval”
- LinkedLinked via arxiv author · 85%Wen-Chih Peng →
“VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval”
- LinkedLinked via arxiv author · 85%An-Zi Yen →
“VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval”
- FuzzySimilar title/name (fuzzy) · 59%BlockRunAI/ClawRouter →
“Fuzzy title match (0.73): “VDAR-Router: Adaptive LLMs Routing via Verbalized Query Diff” ≈ “BlockRunAI/ClawRouter””