Routing

1.RouteLLM: Learning to Route LLMs with Preference Data

post-thumbnail

2.Cost-Effective Online Multi-LLM Selection with Versatile Reward Models

post-thumbnail

3.GRAPHROUTER: A GRAPH-BASED ROUTER FOR LLM SELECTIONS

post-thumbnail

4.Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models

post-thumbnail

5.MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs

post-thumbnail

6.Large Language Model Routing with Benchmark Datasets

post-thumbnail

7.Tryage: Real-time, intelligent Routing of User Prompts to Large Language Models

post-thumbnail

8.AutoMix: Automatically Mixing Language Models

post-thumbnail

9.Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach

post-thumbnail

10.PickLLM: Context-Aware RL-Assisted Large Language Model Routing

post-thumbnail

11.ROUTOO: LEARNING TO ROUTE TO LARGE LANGUAGE MODELS EFFECTIVELY

post-thumbnail

12.REROUTING LLM ROUTERS

post-thumbnail

13.LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing

post-thumbnail

14.CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing

post-thumbnail

15.LLM-Based Routing in Mixture of Experts: A Novel Framework for Trading

post-thumbnail

16.CARROT: A Cost-Aware Rate-Optimal Router

post-thumbnail

17.MixLLM: Mixed Large Language Models

post-thumbnail

18.Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing

post-thumbnail

19.RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs

post-thumbnail

20.Collaborative Speculative Inference for Efficient LLM Inference Serving

post-thumbnail

21.ROUTERRETRIEVER: Routing over a Mixture of Expert Embedding Models

post-thumbnail

22.Learning to Decode Collaboratively with Multiple Language Models

post-thumbnail

23.Efficient Hybrid Inference for LLMs: Reward-Based Token Modelling with Selective Cloud Assistance

post-thumbnail

24.Universal Model Routing for Efficient LLM Inference

post-thumbnail

25.Collaborative Decoding of Critical Tokens for Boosting Factuality of LLMs

post-thumbnail

26.Smoothie: Label Free Language Model Routing

post-thumbnail

27.MasRouter: Learning to Route LLMs for Multi-Agent Systems

post-thumbnail

28.Dynamic LLM Routing and Selection based on User Preferences: Balancing Performance, Cost, and Ethics

post-thumbnail

29.IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory

post-thumbnail

30.Token Level Routing Inference System for Edge Devices

post-thumbnail

31.Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning

post-thumbnail

32.Route-and-Reason (R2-Reasoner)

post-thumbnail

33.CP-Router: An Uncertainty-Aware Router Between LLM and LRM

post-thumbnail

34.RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models

post-thumbnail

35.OmniRouter: Budget and Performance Controllable Multi-LLM Routing

post-thumbnail

36.DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router

post-thumbnail

37.BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute

post-thumbnail

38.Firewall Routing: Blocking Leads to Better Hybrid Inference for LLMs

post-thumbnail

39.Learning from Diverse Reasoning Paths with Routing and Collaboration

post-thumbnail

40.SELECT-THEN-ROUTE: Taxonomy guided Routing for LLMs

post-thumbnail

41.SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context

post-thumbnail

42.RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing

post-thumbnail

43.Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection

post-thumbnail

44.R2R (Roads to Rome): Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

post-thumbnail