Route First, See Later: Enabling Vision Agents to Reason Scientifically by Separating Routing Policy from Action Spaces
cs.CV, cs.AI
Submitted: 2026-11-04
Updated: 2026-11-06
Terminology
Sources
- Agentic-J: An AI Agent for Biological Microscopy Image Analysis
- Schema-Bound LLM Control of Scientific Instrumentation through Model Context Protocol Skills
- ReAct: Synergizing Reasoning and Acting in Language Models
- Toolformer: Language Models Can Teach Themselves to Use Tools
- An LLM Compiler for Parallel Function Calling
- ViperGPT: Visual Inference via Python Execution for Reasoning
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- Learning Compositional Meta-Routing for Agentic Workflows: An Executable Benchmark
- VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs