cs.CVNov 4, 2026

Route First, See Later: Enabling Vision Agents to Reason Scientifically by Separating Routing Policy from Action Spaces

Authors: Shubhabrata Mukherjee, Jeffrey Donatelli, Daniela Ushizima

Organizations: Lawrence Berkeley National Laboratory, , Berkeley, 94720, CA, United States · University of California, San Francisco, , San Francisco, 94143, CA, United States · University of California, Berkeley, , Berkeley, 94720, CA, United States

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.

Figures & tables

Explore similar work

CardsList
  1. Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning

    Jun 11, 2026Changye Li, Meng Lu, Yi Wu +1Tool Use in VLMsVisual Spatial Reasoning

  2. VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies

    May 28, 2026Mingjian Gao, Wenqiao Zhang, Yuqian Yuan +9Efficient VLM InferenceEfficient VLA Inference

  3. Explainable Model Routing for Agentic Workflows

    Apr 4, 2026Mika Okamoto, Ansel Kaplan Erol, Mark RiedlLLM Agent RoutingAgentic Workflows