Saved in:
Bibliographic Details
Main Authors: Liu, Shanyv, Yuan, Xuyang, Chen, Tao, Zhan, Zijun, Han, Zhu, Zheng, Danyang, Zhang, Weishan, Cao, Shaohua
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.19793
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908792179916800
author Liu, Shanyv
Yuan, Xuyang
Chen, Tao
Zhan, Zijun
Han, Zhu
Zheng, Danyang
Zhang, Weishan
Cao, Shaohua
author_facet Liu, Shanyv
Yuan, Xuyang
Chen, Tao
Zhan, Zijun
Han, Zhu
Zheng, Danyang
Zhang, Weishan
Cao, Shaohua
contents Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTER (Context-Aware Strategy for Task Efficient Routing), a lightweight router for dynamic model selection in graph-based MAS. CASTER employs a Dual-Signal Router that combines semantic embeddings with structural meta-features to estimate task difficulty. During training, the router self-optimizes through a Cold Start to Iterative Evolution paradigm, learning from its own routing failures via on-policy negative feedback. Experiments using LLM-as-a-Judge evaluation across Software Engineering, Data Analysis, Scientific Discovery, and Cybersecurity demonstrate that CASTER reduces inference cost by up to 72.4% compared to strong-model baselines while matching their success rates, and consistently outperforms both heuristic routing and FrugalGPT across all domains.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19793
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing
Liu, Shanyv
Yuan, Xuyang
Chen, Tao
Zhan, Zijun
Han, Zhu
Zheng, Danyang
Zhang, Weishan
Cao, Shaohua
Artificial Intelligence
Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTER (Context-Aware Strategy for Task Efficient Routing), a lightweight router for dynamic model selection in graph-based MAS. CASTER employs a Dual-Signal Router that combines semantic embeddings with structural meta-features to estimate task difficulty. During training, the router self-optimizes through a Cold Start to Iterative Evolution paradigm, learning from its own routing failures via on-policy negative feedback. Experiments using LLM-as-a-Judge evaluation across Software Engineering, Data Analysis, Scientific Discovery, and Cybersecurity demonstrate that CASTER reduces inference cost by up to 72.4% compared to strong-model baselines while matching their success rates, and consistently outperforms both heuristic routing and FrugalGPT across all domains.
title CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing
topic Artificial Intelligence
url https://arxiv.org/abs/2601.19793