Visual Orchestration Tax in Agentic VLM Pipelines: Auditing and Certifying Visual Evidence Reuse
cs.MA, cs.CV
Submitted: 2026-10-06
Updated: 2026-10-06
Sources
- VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference
- Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective
- Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning
- KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
- GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning
- SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning In Text-only LLMs
Related papers
- Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
- ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents
- You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
- Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
- MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
- PeroMAS: A Multi-agent System of Perovskite Material Discovery