Pre-Route elicits LLMs' latent routing skills via structured prompts on metadata to proactively choose RAG or long-context, outperforming reactive baselines on cost-effectiveness.
Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong Park
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Frontier LLMs solve single-needle retrieval at 1M tokens on classical Chinese but show three distinct accuracy-decay patterns in three-hop reasoning between 256K and 1M tokens.
citing papers explorer
-
Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection
Pre-Route elicits LLMs' latent routing skills via structured prompts on metadata to proactively choose RAG or long-context, outperforming reactive baselines on cost-effectiveness.
-
Retrieval and Multi-Hop Reasoning in 1M-Token Context Windows: Evaluating LLMs on Classical Chinese Text
Frontier LLMs solve single-needle retrieval at 1M tokens on classical Chinese but show three distinct accuracy-decay patterns in three-hop reasoning between 256K and 1M tokens.