Imagen de Portada

Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Yuanzhe, Deng, Jianing, Hu, Jingtong, Chen, Tianlong, Wang, Song, Yang, Huanrui
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
por: Deng, Jianing, et al.
Publicado: (2026)

FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference
por: Wang, Dongwei, et al.
Publicado: (2025)

Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
por: Hu, Yuanzhe, et al.
Publicado: (2025)

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
por: Hu, Tianyu, et al.
Publicado: (2025)

Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization
por: Wang, Dongwei, et al.
Publicado: (2024)

DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis
por: Wang, Pan, et al.
Publicado: (2024)

MixLLM: Dynamic Routing in Mixed Large Language Models
por: Wang, Xinyuan, et al.
Publicado: (2025)

Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization
por: Wang, Xudong, et al.
Publicado: (2026)

Effective and Efficient Mixed Precision Quantization of Speech Foundation Models
por: Xu, Haoning, et al.
Publicado: (2025)

RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents
por: Wang, Jize, et al.
Publicado: (2026)

Efficient Dynamic Ensembling for Multiple LLM Experts
por: Hu, Jinwu, et al.
Publicado: (2024)

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction
por: Wang, Song, et al.
Publicado: (2025)

MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning
por: Zhang, Yutong, et al.
Publicado: (2026)

RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference
por: Gautam, Arpit Singh, et al.
Publicado: (2026)

MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
por: Wang, Dongwei, et al.
Publicado: (2026)

RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments
por: Zhang, Linghua, et al.
Publicado: (2026)

From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation
por: Ren, Yuxin, et al.
Publicado: (2026)

Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration
por: Yun, Sukwon, et al.
Publicado: (2026)

MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings
por: Zhang, Yiqun, et al.
Publicado: (2026)

Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent
por: Chen, Bo, et al.
Publicado: (2024)

OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction
por: Hu, Junxing, et al.
Publicado: (2026)

LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing
por: Li, Hao, et al.
Publicado: (2026)

D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving
por: Wang, Haodong, et al.
Publicado: (2025)

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
por: Li, Pingzhi, et al.
Publicado: (2023)

IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory
por: Song, Wei, et al.
Publicado: (2025)

SARHAchat: An LLM-Based Chatbot for Sexual and Reproductive Health Counseling
por: Yang, Jiaye, et al.
Publicado: (2025)

RouterBench: A Benchmark for Multi-LLM Routing System
por: Hu, Qitian Jason, et al.
Publicado: (2024)

Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder
por: Xu, Zhen, et al.
Publicado: (2025)

D$^3$: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training
por: Xu, Yuanjian, et al.
Publicado: (2026)

Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement
por: Zhang, Yunjian, et al.
Publicado: (2026)

SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading
por: Shen, Yuanzhe, et al.
Publicado: (2025)

Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning
por: Wang, Chaojie, et al.
Publicado: (2024)

Orchestrating Intelligence: Confidence-Aware Routing for Efficient Multi-Agent Collaboration across Multi-Scale Models
por: Wang, Jingbo, et al.
Publicado: (2026)

ICL-Router: In-Context Learned Model Representations for LLM Routing
por: Wang, Chenxu, et al.
Publicado: (2025)

RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
por: Liu, Jun, et al.
Publicado: (2025)

DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans
por: Yao, Bingsheng, et al.
Publicado: (2025)

AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactions
por: Chen, Minghao, et al.
Publicado: (2026)

PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization
por: Wang, Xinhai, et al.
Publicado: (2025)

CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks
por: Wang, Tianlong, et al.
Publicado: (2024)

DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching
por: Lu, Yuxing, et al.
Publicado: (2026)