SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.04203 · ICLR · 2025

MMRole: A COMPREHENSIVE FRAMEWORK FOR DEVELOPING AND EVALUATING MULTIMODAL ROLE-PLAYING AGENTS

Zhiwu Lu, Xu Chen, Lei Wang, Yanqi Dai, Huanran Hu, Shengjie Jin, Character Info, Harry Potter, Alex Zhang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2408.04203.json · badge: /api/ran/2408.04203.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
yanqidai/mmrole canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_review_score Ran
ran, honoured the contract we drafted
yanqidai/mmrole/eval/RM_review.py
code served (permissive licence) · get_code("a21bd372559fcd45")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

# Analyze the function: get_review_score expects a string parameter 'review'
# The function splits the string, processes it to extract score pairs
# It expects a format like: "....[Scores]:\n(score1, score2)"

review_string = """
Some review text here.
[Scores]:
(8.5, 9.2)
"""

ARGS = {
    'review': review_string
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
preprocess Ran
ran; our contract draft was wrong, not the code
yanqidai/mmrole/finetune.py
code served (permissive licence) · get_code("8b733c9fc590e4c1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import transformers
from transformers.trainer_pt_utils import LabelSmoother

torch.manual_seed(0)

class MockTokenizer:
    def __init__(self):
        self.im_start_id = 100
        self.im_end_id = 101
        self.pad_token_id = 0
        self._token_to_ids = {
            'system': [102],
            'user': [103],
            'assistant': [104],
            '\n': [105],
            'You are a helpful assistant.': [106, 107],
            'Hello': [108, 109],
            'Hi there': [110, 111, 112],
        }
    
    def __call__(self, text):
        if text in self._token_to_ids:
            return type('obj', (object,), {'input_ids': self._token_to_ids[text]})()
        return type('obj', (object,), {'input_ids': [113]})()

tokenizer = MockTokenizer()

sources = [
    [
        {'from': 'user', 'value': 'Hello'},
        {'from': 'assistant', 'value': 'Hi there'},
    ],
    [
        {'from': 'user', 'value': 'Hello'},
        {'from': 'assistant', 'value': 'Hi there'},
    ],
]

ARGS = {
    'sources': sources,
    'tokenizer': tokenizer,
    'max_len': 64,
    'system_message': 'You are a helpful assistant.',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 1 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.

FunctionAlso present inEarliest-datedOthers named
preprocess 8 other papers
6 dated earlier, 2 later
2311.09198 (2023-11)
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training
2401.10935 (2024-01)
SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
2402.11905 (2024-02)
Learning to Edit: Aligning LLMs with Knowledge Editing
and 5 more not named here

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

Recently, Role-Playing Agents (RPAs) have garnered increasing attention for their potential to deliver emotional value and facilitate sociological research. However, existing studies are primarily confined to the textual modality, unable to simulate humans' multimodal perceptual capabilities. To bridge this gap, we introduce the concept of Multimodal Role-Playing Agents (MRPAs), and propose a comprehensive framework, MMRole, for their development and evaluation, which comprises a personalized multimodal dataset and a robust evaluation approach. Specifically, we construct a large-scale, high-quality dataset, MMRole-Data, consisting of 85 characters, 11K images, and 14K single or multi-turn dialogues. Additionally, we present a robust evaluation approach, MMRole-Eval, encompassing eight metrics across three dimensions, where a reward model is designed to score MRPAs with the constructed ground-truth data for comparison. Moreover, we develop the first specialized MRPA, MMRole-Agent. Extensive evaluation results demonstrate the improved performance of MMRole-Agent and highlight the primary challenges in developing MRPAs, emphasizing the need for enhanced multimodal understanding and role-playing consistency. The data, code, and models are all available. 1

For agents

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

get_harvested_code_for_paper("2408.04203")
get_code_for_paper("2408.04203")
have("2408.04203")

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

curl https://syntology.ai/api/ran/2408.04203.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.04203.svg)](https://syntology.ai/paper/2408.04203)

Connect an agent — have() is free.