SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.11085 · ECCV · 2024

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

Jieyu Zhang, Zixian Ma, Ranjay Krishna, Weikai Huang, Tanmay Gupta

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 8 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.11085.json · badge: /api/ran/2403.11085.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
RAIVNLab/mms canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
raivnlab/mnms canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
checks_terminate_message Ran
ran, violated the contract we drafted
raivnlab/mnms/mnms/run_plan_agent.py
pointer only (licence: NONE) · get_code("9c26cc8e53781756")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raivnlab/mnms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_node_patterns Ran
ran; our contract draft was wrong, not the code
RAIVNLab/mms/mnms/verifier.py
pointer only (licence: NONE) · get_code("cd95a2581690e761")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RAIVNLab/mms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

flatten_labels Ran
ran; our contract draft was wrong, not the code
RAIVNLab/mms/mnms/evaluation/metrics.py
pointer only (licence: NONE) · get_code("bf0b50da342cb58e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RAIVNLab/mms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

format_python_str Ran
ran; our contract draft was wrong, not the code
RAIVNLab/mms/mnms/prompt.py
pointer only (licence: NONE) · get_code("6bb1d852d31d4d01")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RAIVNLab/mms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

nodes_to_code Ran
ran; our contract draft was wrong, not the code
RAIVNLab/mms/mnms/evaluation/evaluator.py
pointer only (licence: NONE) · get_code("1a468c0ba7ba78eb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RAIVNLab/mms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

nodes_to_program Ran
ran; our contract draft was wrong, not the code
RAIVNLab/mms/mnms/prompt.py
pointer only (licence: NONE) · get_code("5e9856951ad7a58e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RAIVNLab/mms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

object_processing Ran
ran; our contract draft was wrong, not the code
RAIVNLab/mms/mnms/execution/tool_api.py
pointer only (licence: NONE) · get_code("cd58034ecc1945fe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RAIVNLab/mms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_data_from_file Ran
ran; our contract draft was wrong, not the code
raivnlab/mnms/mnms/run_plan_agent.py
pointer only (licence: NONE) · get_code("5822609079590d9e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raivnlab/mnms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

replace_node_with_placeholder Ran
ran; our contract draft was wrong, not the code
RAIVNLab/mms/mnms/evaluation/evaluator.py
pointer only (licence: NONE) · get_code("76350c7f8fa4a0c6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RAIVNLab/mms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_best_match Not yet run
unverified (harvested, no recorded run)
RAIVNLab/mms/mnms/evaluation/evaluator.py
pointer only (licence: NONE) · get_code("0776d0fd85848acd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RAIVNLab/mms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_full_path_data Not yet run
unverified (harvested, no recorded run)
RAIVNLab/mms/mnms/execution/tool_api.py
pointer only (licence: NONE) · get_code("f7710cfb5c0415cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RAIVNLab/mms when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 11 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 and provide practical recommendations for designing planners for multi-step multi-modal tasks. Our dataset and evaluation code are available on HuggingFace 3 and Github 4 respectively.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.11085")
get_code_for_paper("2403.11085")
have("2403.11085")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.11085.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.11085.svg)](https://syntology.ai/paper/2403.11085)

Connect an agent — have() is free.