# m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks

arXiv: https://arxiv.org/abs/2403.11085 · HTML: https://mlsanity.com/paper/2403.11085/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 52 references that are in the map.
- First posted on arXiv 17 Mar 2024.

## Builds on (most cited first, 30 of 35)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning](https://mlsanity.com/paper/2307.06135/) (2023)
- [Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory](https://mlsanity.com/paper/2305.17144/) (2023)
- [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023)
- [AdaPlanner: Adaptive Planning from Feedback with Language Models](https://mlsanity.com/paper/2305.16653/) (2023)
- [SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning](https://mlsanity.com/paper/2308.00436/) (2023)
- [TaskBench: Benchmarking Large Language Models for Task Automation](https://mlsanity.com/paper/2311.18760/) (2023)
- [AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn](https://mlsanity.com/paper/2306.08640/) (2023)
- [Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning](https://mlsanity.com/paper/1907.09620/) (2019)
- [EcoAssistant: Using LLM Assistant More Affordably and Accurately](https://mlsanity.com/paper/2310.03046/) (2023)

## Built on by (most cited first, 30 of 38)

- [Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models](https://mlsanity.com/paper/2406.09403/) (2024)
- [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [GTA: A Benchmark for General Tool Agents](https://mlsanity.com/paper/2407.08713/) (2024)
- [ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks](https://mlsanity.com/paper/2505.23752/) (2025)
- [Adaptive In-conversation Team Building for Language Model Agents](https://mlsanity.com/paper/2405.19425/) (2024)
- [Explain Before You Answer: A Survey on Compositional Visual Reasoning](https://mlsanity.com/paper/2508.17298/) (2025)
- [DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback](https://mlsanity.com/paper/2410.06215/) (2024)
- [Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents](https://mlsanity.com/paper/2510.02837/) (2025)
- [Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)](https://mlsanity.com/paper/2504.03151/) (2025)
- [AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios](https://mlsanity.com/paper/2602.23166/) (2026)
- [PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure Cases](https://mlsanity.com/paper/2509.25238/) (2025)
- [SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL](https://mlsanity.com/paper/2512.04069/) (2025)
- [ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning](https://mlsanity.com/paper/2603.12740/) (2026)
- [LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls](https://mlsanity.com/paper/2511.09148/) (2025)
- [Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage](https://mlsanity.com/paper/2510.02044/) (2025)
- [T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning](https://mlsanity.com/paper/2505.16986/) (2025)
- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools](https://mlsanity.com/paper/2508.03284/) (2025)
- [EcoAct: Economic Agent Determines When to Register What Action](https://mlsanity.com/paper/2411.01643/) (2024)
- [CodeNav: Beyond tool-use to using real-world codebases with LLM agents](https://mlsanity.com/paper/2406.12276/) (2024)
- [Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training](https://mlsanity.com/paper/2502.06589/) (2025)
- [Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations](https://mlsanity.com/paper/2605.11633/) (2026)
- [Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?](https://mlsanity.com/paper/2604.03016/) (2026)
- [Sustainability assessment using multimodal AI agents](https://mlsanity.com/paper/2507.17012/) (2025)
- [From Tool Orchestration to Code Execution: A Study of MCP Design Choices](https://mlsanity.com/paper/2602.15945/) (2026)
- [GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows](https://mlsanity.com/paper/2604.15715/) (2026)
- [SEAL: Suite for Evaluating API-use of LLMs](https://mlsanity.com/paper/2409.15523/) (2024)
- [A Survey on Complex Tasks for Goal-Directed Interactive Agents](https://mlsanity.com/paper/2409.18538/) (2024)
- [MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models](https://mlsanity.com/paper/2507.23382/) (2025)

## Abstract (arXiv)

Real-world multi-modal problems are rarely solved by a single machine learning model, and often require multi-step computational plans that involve stitching several models. Tool-augmented LLMs hold tremendous promise for automating the generation of such computational plans. However, the lack of standardized benchmarks for evaluating LLMs as planners for multi-step multi-modal tasks has prevented a systematic study of planner design decisions. Should LLMs generate a full plan in a single shot or step-by-step? Should they invoke tools directly with Python code or through structured data formats like JSON? Does feedback improve planning? To answer these questions and more, we introduce m&m's: a benchmark containing 4K+ multi-step multi-modal tasks involving 33 tools that include multi-modal models, (free) public APIs, and image processing modules. For each of these task queries, we provide automatically generated plans using this realistic toolset. We further provide a high-quality subset of 1,565 task plans that are human-verified and correctly executable. With m&m's, we evaluate 10 popular LLMs with 2 planning strategies (multi-step vs. step-by-step planning), 2 plan formats (JSON vs. code), and 3 types of feedback (parsing/verification/execution). Finally, we summarize takeaways from our extensive experiments. Our dataset and code are available on HuggingFace (https://huggingface.co/datasets/zixianma/mnms) and Github (https://github.com/RAIVNLab/mnms).