Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection
Fuente:
arXiv
Saved in:
| Main Authors: | Chen, Yiwen, Li, Kuan, Zhuang, Fuzhen, Wang, Deqing, Zhang, Zhao, Zhang, Liwen, Jiang, Yong, Wang, Shuai, Cheng, Minhao |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing
by: Li, Kuan, et al.
Published: (2025)
by: Li, Kuan, et al.
Published: (2025)
Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenario
by: Mu, Feiteng, et al.
Published: (2024)
by: Mu, Feiteng, et al.
Published: (2024)
Unsupervised Query Routing for Retrieval Augmented Generation
by: Mu, Feiteng, et al.
Published: (2025)
by: Mu, Feiteng, et al.
Published: (2025)
UniFAR: A Unified Facet-Aware Retrieval Framework for Scientific Documents
by: Dou, Zheng, et al.
Published: (2026)
by: Dou, Zheng, et al.
Published: (2026)
One for Dozens: Adaptive REcommendation for All Domains with Counterfactual Augmentation
by: Luo, Huishi, et al.
Published: (2024)
by: Luo, Huishi, et al.
Published: (2024)
CDC: Causal Domain Clustering for Multi-Domain Recommendation
by: Luo, Huishi, et al.
Published: (2025)
by: Luo, Huishi, et al.
Published: (2025)
TextBridgeGNN: Pre-training Graph Neural Network for Cross-Domain Recommendation via Text-Guided Transfer
by: Chen, Yiwen, et al.
Published: (2025)
by: Chen, Yiwen, et al.
Published: (2025)
Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization
by: Wu, Di, et al.
Published: (2025)
by: Wu, Di, et al.
Published: (2025)
ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
by: Wu, Xixi, et al.
Published: (2025)
by: Wu, Xixi, et al.
Published: (2025)
LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation
by: Chen, Yiwen, et al.
Published: (2026)
by: Chen, Yiwen, et al.
Published: (2026)
Long Context vs. RAG for LLMs: An Evaluation and Revisits
by: Li, Xinze, et al.
Published: (2024)
by: Li, Xinze, et al.
Published: (2024)
RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs
by: Fernandez, Nigel, et al.
Published: (2025)
by: Fernandez, Nigel, et al.
Published: (2025)
FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generation
by: Wang, Shuai, et al.
Published: (2024)
by: Wang, Shuai, et al.
Published: (2024)
Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference
by: Xiao, Qingfa, et al.
Published: (2025)
by: Xiao, Qingfa, et al.
Published: (2025)
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
by: Feng, Zhaopeng, et al.
Published: (2026)
by: Feng, Zhaopeng, et al.
Published: (2026)
SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context
by: Wang, Hairu, et al.
Published: (2025)
by: Wang, Hairu, et al.
Published: (2025)
FLeW: Facet-Level and Adaptive Weighted Representation Learning of Scientific Documents
by: Dou, Zheng, et al.
Published: (2025)
by: Dou, Zheng, et al.
Published: (2025)
Bridging Social Psychology and LLM Reasoning: Conflict-Aware Meta-Review Generation via Cognitive Alignment
by: Chen, Wei, et al.
Published: (2025)
by: Chen, Wei, et al.
Published: (2025)
PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
by: Geng, Runpeng, et al.
Published: (2025)
by: Geng, Runpeng, et al.
Published: (2025)
Resolving the Robustness-Precision Trade-off in Financial RAG through Hybrid Document-Routed Retrieval
by: Cheng, Zhiyuan, et al.
Published: (2026)
by: Cheng, Zhiyuan, et al.
Published: (2026)
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
by: Jiang, Ziyan, et al.
Published: (2024)
by: Jiang, Ziyan, et al.
Published: (2024)
RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing
by: Wang, Ziqi, et al.
Published: (2026)
by: Wang, Ziqi, et al.
Published: (2026)
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
by: Yu, Yue, et al.
Published: (2024)
by: Yu, Yue, et al.
Published: (2024)
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory
by: Tang, Zihao, et al.
Published: (2026)
by: Tang, Zihao, et al.
Published: (2026)
SelRoute: Query-Type-Aware Routing for Long-Term Conversational Memory Retrieval
by: McKee, Matthew
Published: (2026)
by: McKee, Matthew
Published: (2026)
Parametric Retrieval-Augmented Generation using Latent Routing of LoRA Adapters
by: Su, Zhan, et al.
Published: (2025)
by: Su, Zhan, et al.
Published: (2025)
MLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation
by: Zhang, Yongyue, et al.
Published: (2026)
by: Zhang, Yongyue, et al.
Published: (2026)
Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection
by: Pan, Zhihong, et al.
Published: (2025)
by: Pan, Zhihong, et al.
Published: (2025)
RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning
by: Guo, Yucan, et al.
Published: (2025)
by: Guo, Yucan, et al.
Published: (2025)
Dynamic Latent Routing
by: Yu, Fangyuan, et al.
Published: (2026)
by: Yu, Fangyuan, et al.
Published: (2026)
Long$^2$RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall
by: Qi, Zehan, et al.
Published: (2024)
by: Qi, Zehan, et al.
Published: (2024)
Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding
by: Shim, Seongwoong, et al.
Published: (2025)
by: Shim, Seongwoong, et al.
Published: (2025)
SymRAG: Efficient Neuro-Symbolic Retrieval Through Adaptive Query Routing
by: Hakim, Safayat Bin, et al.
Published: (2025)
by: Hakim, Safayat Bin, et al.
Published: (2025)
MasRouter: Learning to Route LLMs for Multi-Agent Systems
by: Yue, Yanwei, et al.
Published: (2025)
by: Yue, Yanwei, et al.
Published: (2025)
Analytical Searching vs. Browsing in Hypertext Information Retrieval Systems.
by: Qiu, Liwen
Published: (1993)
by: Qiu, Liwen
Published: (1993)
Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
by: Jin, Bowen, et al.
Published: (2024)
by: Jin, Bowen, et al.
Published: (2024)
SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
by: Kim, Junho, et al.
Published: (2024)
by: Kim, Junho, et al.
Published: (2024)
Privacy-Preserving LLMs Routing
by: Wu, Xidong, et al.
Published: (2026)
by: Wu, Xidong, et al.
Published: (2026)
FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning
by: Chen, Wei, et al.
Published: (2024)
by: Chen, Wei, et al.
Published: (2024)
Hyperbolic Diffusion Recommender Model
by: Yuan, Meng, et al.
Published: (2025)
by: Yuan, Meng, et al.
Published: (2025)
Similar Items
-
LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing
by: Li, Kuan, et al.
Published: (2025) -
Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenario
by: Mu, Feiteng, et al.
Published: (2024) -
Unsupervised Query Routing for Retrieval Augmented Generation
by: Mu, Feiteng, et al.
Published: (2025) -
UniFAR: A Unified Facet-Aware Retrieval Framework for Scientific Documents
by: Dou, Zheng, et al.
Published: (2026) -
One for Dozens: Adaptive REcommendation for All Domains with Counterfactual Augmentation
by: Luo, Huishi, et al.
Published: (2024)