# DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning

arXiv: https://arxiv.org/abs/2512.07132 · HTML: https://mlsanity.com/paper/2512.07132/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 31 of its 58 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 31)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [TALM: Tool Augmented Language Models](https://mlsanity.com/paper/2205.12255/) (2022)
- [Ovis: Structural Embedding Alignment for Multimodal Large Language Model](https://mlsanity.com/paper/2405.20797/) (2024)
- [ExpertPrompting: Instructing Large Language Models to be Distinguished Experts](https://mlsanity.com/paper/2305.14688/) (2023)
- [ProAgent: Building Proactive Cooperative Agents with Large Language Models](https://mlsanity.com/paper/2308.11339/) (2023)
- [CodeAgent: Autonomous Communicative Agents for Code Review](https://mlsanity.com/paper/2402.02172/) (2024)
- [MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning](https://mlsanity.com/paper/2402.17231/) (2024)
- [ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration](https://mlsanity.com/paper/2411.00053/) (2024)
- [An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making](https://mlsanity.com/paper/2410.15168/) (2024)
- [EVINCE: Optimizing Multi-LLM Dialogues Using Conditional Statistics and Information Theory](https://mlsanity.com/paper/2408.14575/) (2024)
- [MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation](https://mlsanity.com/paper/2506.17113/) (2025)
- [PEAR: A Robust and Flexible Automation Framework for Ptychography Enabled by Multiple Large Language Model Agents](https://mlsanity.com/paper/2410.09034/) (2024)
- [AIDE: Agentically Improve Visual Language Model with Domain Experts](https://mlsanity.com/paper/2502.09051/) (2025)
- [Hydra: An Agentic Reasoning Approach for Enhancing Adversarial Robustness and Mitigating Hallucinations in Vision-Language Models](https://mlsanity.com/paper/2504.14395/) (2025)

## Built on by (most cited first, 5 of 5)

- [Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidence](https://mlsanity.com/paper/2605.30698/) (2026)
- [Vision Verification Enhanced Fusion of VLMs for Efficient Visual Reasoning](https://mlsanity.com/paper/2603.12669/) (2026)
- [Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility](https://mlsanity.com/paper/2607.14108/) (2026)
- [ReTAC: Residual Test-Time Agentic Computation for Video Spatial Reasoning](https://mlsanity.com/paper/2610.16315/) (2026)
- [ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps](https://mlsanity.com/paper/2610.20532/) (2026)

## Abstract (arXiv)

Specialized visual tools can augment large language models or vision language models with expert knowledge (e.g., grounding, spatial reasoning, medical knowledge, etc.), but knowing which tools to call (and when to call them) can be challenging. We introduce DART, a multi-agent framework that uses disagreements between multiple debating visual agents to identify useful visual tools (e.g., object detection, OCR, spatial reasoning, etc.) that can resolve inter-agent disagreement. These tools allow for fruitful multi-agent discussion by introducing new information, and by providing tool-aligned agreement scores that highlight agents in agreement with expert tools, thereby facilitating discussion. We utilize an aggregator agent to select the best answer by providing the agent outputs and tool information. We test DART on four diverse benchmarks and show that our approach improves over multi-agent debate as well as over single agent tool-calling frameworks, beating the next-strongest baseline (multi-agent debate with a judge model) by 3.4% and 2.4% on A-OKVQA and MMMU respectively. We also find that DART adapts well to new tools in applied domains, with a 1.3% improvement on the M3D medical dataset over other strong tool-calling, single agent, and multi-agent baselines. Additionally, we measure text overlap across rounds to highlight the rich discussion in DART compared to existing multi-agent methods. Finally, we study the tool call distribution, finding that diverse tools are reliably used to help resolve disagreement.