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

DevFeed: [Route First, See Later: Enabling Vision Agents to Reason Scientifically by Separating Routing Policy from Action Spaces](<https://devfeed.tech/articles/route-first-see-later-enabling-vision-agents-to-reason-scientifically-by-separating-routing-policy-from-action-spaces-118506.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06760>)

Author: Shubhabrata Mukherjee, Jeffrey Donatelli, Daniela Ushizima

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [qwen](<https://devfeed.tech/topics/qwen.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [auditability](<https://devfeed.tech/tags/auditability.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [decoupling](<https://devfeed.tech/tags/decoupling.md>), [detection](<https://devfeed.tech/tags/detection.md>), [errors](<https://devfeed.tech/tags/errors.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [execution](<https://devfeed.tech/tags/execution.md>), [image-analysis](<https://devfeed.tech/tags/image-analysis.md>), [isolates](<https://devfeed.tech/tags/isolates.md>), [legal](<https://devfeed.tech/tags/legal.md>), [legal-action](<https://devfeed.tech/tags/legal-action.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [models](<https://devfeed.tech/tags/models.md>), [policy](<https://devfeed.tech/tags/policy.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [routing](<https://devfeed.tech/tags/routing.md>), [routing-policy](<https://devfeed.tech/tags/routing-policy.md>), [vision](<https://devfeed.tech/tags/vision.md>)

## AI overview

ZETA separates scientific intent routing from visual-tool execution, making misrouting distinguishable from perception or execution failures. It resolves the requested capability before invoking specialized tools and treats measurement as a deterministic operation based on explicit geometry. In a zero-shot benchmark of 51 scientific-intent queries, specifying routing semantics improved accuracy, especially between semantically adjacent actions, though gains varied by model. For Qwen 3.8, segmentation routing rose from 6.2% to 75.0% and detection routing from 60.0% to 100%. Execution traces expose routing decisions and downstream artifacts separately. The supplied abstract does not report full-document details or broader benchmark results.

## Source excerpt

arXiv:2611.06760v1 Announce Type: cross 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.