跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 28 天前AI 評分46

AgentBaton:智能體任務中的高效模型協作

AgentBaton: Efficient Model Collaboration in Agentic Tasks

AI 導讀

AgentBaton 探討在長程智能體任務中,讓能力較強與效率較高的模型在合適階段交接,以降低成本並維持準確度。它在 11 對模型及兩個代表性基準測試中,平均降低 API 成本 65.9%,準確度最高較只用能力較強模型提升 8.8 個百分點,並擴展準確度與成本的 Pareto 前沿。

正文

Published on Oct 25

Authors:

,

,

,

,

,

,

,

Abstract

Capable-to-efficient model handoffs at suitable task stages preserve accuracy while cutting costs, and a lightweight detector, AgentBaton, achieves large API cost savings and extends the accuracy-cost Pareto frontier.

Solving long-horizon agentic tasks requires language agents to interact with their environments over multiple steps, and reliable performance often comes from the expensive capable models available through cloud providers. Meanwhile, alternative efficient models with inferior performance but a much lower cost are emerging, including lower-tier cloud models and smaller open-weights models deployable on local hardware. This raises a natural question that remains less explored than traditional query-level routing: can capable and efficient models collaborate within a single long-horizon agentic task to substantially reduce cost while preserving task accuracy? In this paper, we systematically investigate key design choices for such collaboration through model handoffs, where one model takes over from another, focusing on handoff direction and context transfer. We find that efficient-to-capable handoffs generally underperform capable-only execution with limited or even no cost reduction, whereas capable-to-efficient handoffs at suitable stages of task progress largely preserve or even improve accuracy while substantially reducing cost. These findings suggest that a one-time, simple, well-timed handoff strategy is good enough for cost-effective agent collaboration, motivating AgentBaton, a lightweight detector that learns when to hand off from recurring patterns in task progress. Across 11 model pairs and two representative benchmarks, AgentBaton reduces API costs by 65.9% on average while largely preserving task accuracy, with accuracy gains of up to 8.8 percentage points over capable-only execution. Experiments across various reasoning-effort settings further show that AgentBaton extends the empirical accuracy-cost Pareto frontier.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.35959

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.35959 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.35959 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.35959 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co