arXiv cs.MA· Pascal Sowietzki, Steffen Holter, Yannick Metz, Emil Kasper, Raphael Baur, Mennatallah El-Assady·· 6 天前AI 评分34
ARIA：让 AI 智能体学会何时向更强模型求助
Ask Your Advisor: Learning When to Consult Stronger Models in Agentic Systems
AI 导读
针对 executor-advisor 系统中执行模型难以自我判断何时求助的问题，研究者提出元控制器 ARIA，将咨询建模为序列化资源分配问题，在工作流接触点选择 SILENT 或 CONSULT，动作价值由蒙特卡洛控制从带成本惩罚的结果中学习。
正文 · 原文
Abstract:To balance task performance and computational cost, agentic workflows can use a lower-cost model for execution and selectively consult a stronger model. In such executor-advisor systems, the executor decides when to seek advice, making escalation depend on self-assessment, although current language models struggle to detect where their own reasoning fails. The need for stronger reasoning emerges during execution and varies across workflow phases. We introduce ARIA, a meta-controller that learns when to consult by balancing task success against consultation cost. Our approach formulates consultation as a sequential resource-allocation problem. At workflow contact points, ARIA maps execution evidence to a compact state abstraction and selects SILENT or CONSULT, with action values learned by Monte Carlo control from cost-penalized outcomes. Across evaluated tasks of SWE-bench Verified, Terminal-Bench 2.1, and $\tau^2$-bench, ARIA recovers 44-81% of the executor-advisor success gap at less than half the advisor model's cost. ARIA achieves the best observed success-cost trade-off among ten other evaluated conditions, including routing and cascading methods, fixed and prompted consultation, and random placement at matched advice volume. The policies are compact and inspectable, with a single consultation-price parameter governing the success-cost trade-off without retraining either underlying model.
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.13870 [cs.MA] |
| (or arXiv:2610.13870v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13870 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Pascal Sowietzki [view email]
[v1]
Fri, 9 Oct 2026 17:19:54 UTC (1,447 KB)
来源：arXiv cs.MA · arxiv.org