mlsanityData to 14 Oct 2026

Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems

arXiv 2601.18735 ↗First posted 26 Jan 2026cs.AI cs.LGcited by 4

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 19 of its 47 references that are in the map. First posted on arXiv 26 Jan 2026.

Builds on

19 of 47 references.

References · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2024GPT-4o System Cardcited by 4,588
  3. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  4. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  5. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  6. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  8. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 438
  9. 2021InfographicVQAcited by 437
  10. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 372
  11. 2024CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacycited by 81
  12. 2025KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systemscited by 37
7 more
  1. 2022Contextual Bandits with Large Action Spaces: Made Practicalcited by 33
  2. 2024Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systemscited by 25
  3. 2022Variance-Aware Sparse Linear Banditscited by 11
  4. 2025Large Language Model-Enhanced Multi-Armed Banditscited by 7
  5. 2024Causal Graphical Models for Vision-Language Compositional Understandingcited by 6
  6. 2022MIX-MAB: Reinforcement Learning-based Resource Allocation Algorithm for LoRaWANcited by 3
  7. 2024Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agentscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agentscited by 2
  2. 2026LogicGaze: Benchmarking Causal Consistency in Visual Narratives via Counterfactual Verificationcited by 0
  3. 2026Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD Perceptioncited by 0
  4. 2026CacheScope: Exact-Compute Allocation for Training-Free Diffusion Accelerationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From Competition to Coordination: Market Making as a Scalable Framework for Safe and Aligned Multi-Agent LLM Systems
  2. 2026Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation
  3. 2025ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination
  4. 2025GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning
  5. 2026AgenticAITA: A Proof-Of-Concept About Deliberative Multi-Agent Reasoning for Autonomous Trading Systems
  6. 2025VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
  7. 2026TrustTrade: Human-Inspired Selective Consensus Reduces Decision Uncertainty in LLM Trading Agents
  8. 2026Learning to Sell: Reinforcement Learning for Strategic Large Language Model Agents in Multi-Product Markets