ZETA 架构：让视觉智能体先把路由策略与动作执行分离，实现科学化推理
Route First, See Later: Enabling Vision Agents to Reason Scientifically by Separating Routing Policy from Action Spaces
AI 导读
论文提出 ZETA 架构，将科学图像分析中智能体的路由策略与视觉工具执行解耦，在调用检测、分割等专用工具前先解析科学意图，使路由错误与执行失败可分别审计。在 51 个科学意图查询的 zero-shot 基准上，Qwen 3.8 显式路由策略使分割路由准确率从 6.2% 升至 75.0%，检测路由准确率从 60.0% 升至 100%。
正文 · 原文
Abstract:Scientific image-analysis workflows require agents to select among diverse capabilities like description, detection, counting, and segmentation. Current multi-tool architectures conflate intent interpretation with visual execution, masking whether a failure arises from flawed reasoning (misrouting) or failed perception (invalid tool execution). This lack of auditability renders agents unreliable for high-stakes scientific automation. We introduce ZETA, an extensible architecture that operationalizes the decoupling of routing policy from action execution. ZETA resolves scientific intent before invoking specialized visual tools, treating measurement as a deterministic operation grounded in explicit geometry rather than generative output. This architecture exposes the "black box" of agent decision-making, allowing routing correctness and downstream execution to be evaluated as independent failure modes.
To our knowledge, we provide the first controlled study in scientific vision-agent routing that isolates explicit routing-policy specification while holding the legal action interface fixed. Evaluation on a zero-shot benchmark of 51 scientific-intent queries shows that explicit routing semantics can substantially improve routing accuracy, particularly at semantically adjacent action boundaries, although improvements vary across models. For Qwen 3.8, explicit routing-policy specification improves segmentation routing accuracy from 6.2% to 75.0% and detection routing accuracy from 60.0% to 100%. ZETA's execution traces make routing decisions and downstream artifacts separately observable, providing a basis for distinguishing intent-selection errors from visual execution failures. ZETA establishes the necessary infrastructure to isolate execution errors from interpretive ones, a critical requirement for deploying reliable scientific vision agents.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06760 [cs.CV] |
| (or arXiv:2611.06760v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06760 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shubhabrata Mukherjee [view email]
[v1]
Wed, 4 Nov 2026 16:39:17 UTC (6,478 KB)
来源：arXiv cs.AI · arxiv.org