Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.18735 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908788991197184 |
|---|---|
| author | Zhang, Jusheng Fan, Yijia Cai, Kaitong Yang, Jing Yao, Jiawei Wang, Jian Qu, Guanlong Chen, Ziliang Wang, Keze |
| author_facet | Zhang, Jusheng Fan, Yijia Cai, Kaitong Yang, Jing Yao, Jiawei Wang, Jian Qu, Guanlong Chen, Ziliang Wang, Keze |
| contents | Vision-Language Models (VLMs) enable powerful multi-agent systems, but scaling them is economically unsustainable: coordinating heterogeneous agents under information asymmetry often spirals costs. Existing paradigms, such as Mixture-of-Agents and knowledge-based routers, rely on heuristic proxies that ignore costs and collapse uncertainty structure, leading to provably suboptimal coordination. We introduce Agora, a framework that reframes coordination as a decentralized market for uncertainty. Agora formalizes epistemic uncertainty into a structured, tradable asset (perceptual, semantic, inferential), and enforces profitability-driven trading among agents based on rational economic rules. A market-aware broker, extending Thompson Sampling, initiates collaboration and guides the system toward cost-efficient equilibria. Experiments on five multimodal benchmarks (MMMU, MMBench, MathVision, InfoVQA, CC-OCR) show that Agora outperforms strong VLMs and heuristic multi-agent strategies, e.g., achieving +8.5% accuracy over the best baseline on MMMU while reducing cost by over 3x. These results establish market-based coordination as a principled and scalable paradigm for building economically viable multi-agent visual intelligence systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18735 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems Zhang, Jusheng Fan, Yijia Cai, Kaitong Yang, Jing Yao, Jiawei Wang, Jian Qu, Guanlong Chen, Ziliang Wang, Keze Artificial Intelligence Machine Learning Vision-Language Models (VLMs) enable powerful multi-agent systems, but scaling them is economically unsustainable: coordinating heterogeneous agents under information asymmetry often spirals costs. Existing paradigms, such as Mixture-of-Agents and knowledge-based routers, rely on heuristic proxies that ignore costs and collapse uncertainty structure, leading to provably suboptimal coordination. We introduce Agora, a framework that reframes coordination as a decentralized market for uncertainty. Agora formalizes epistemic uncertainty into a structured, tradable asset (perceptual, semantic, inferential), and enforces profitability-driven trading among agents based on rational economic rules. A market-aware broker, extending Thompson Sampling, initiates collaboration and guides the system toward cost-efficient equilibria. Experiments on five multimodal benchmarks (MMMU, MMBench, MathVision, InfoVQA, CC-OCR) show that Agora outperforms strong VLMs and heuristic multi-agent strategies, e.g., achieving +8.5% accuracy over the best baseline on MMMU while reducing cost by over 3x. These results establish market-based coordination as a principled and scalable paradigm for building economically viable multi-agent visual intelligence systems. |
| title | Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2601.18735 |