Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing

2024/05/01 by KV Aditya Srivatsa, Srivatsa, KV Aditya, Kaushal Kumar Maurya +3 · 15 citations
Computer Science · #Computation and Language (cs.CL) #Digital Rights Management and Security #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2405.00467

openalex publication_date 2024/05/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

With the rapid development of LLMs, it is natural to ask how to harness their capabilities efficiently. In this paper, we explore whether it is feasible to direct each input query to a single most suitable LLM. To this end, we propose LLM routing for challenging reasoning tasks. Our extensive experiments suggest that such routing shows promise but is not feasible in all scenarios, so more robust approaches should be investigated to fill this gap.

Cited by

• Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process
• Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models
• Teaming LLMs to Detect and Mitigate Hallucinations
• LLM Routing with Dueling Feedback
• Learning Compact Representations of LLM Abilities via Item Response Theory
• Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning
• CTTS: Collective Test-Time Scaling
• Balancing Information Accuracy and Response Timeliness in Networked LLMs
• MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification
• Open-Source LLMs Collaboration Beats Closed-Source LLMs: A Scalable Multi-Agent System
• BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
• TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks
• Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques
• Synergistic Weak-Strong Collaboration by Aligning Preferences
• EMAFusion: A Self-Optimizing System for Seamless LLM Selection and Integration

Related

• Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection
• RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs
• Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers
• Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking
• DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search