Papers › MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for...

MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks

18 May 2025arXiv:2505.12371archive 2025-07-28

Yinghao Zhu, Ziyi He, Haoran Hu, Xiaochen Zheng, Xichen Zhang, Zixiang Wang, Junyi Gao, Liantao Ma, Lequan Yu

The rapid advancement of Large Language Models (LLMs) has stimulated interest in multi-agent collaboration for addressing complex medical tasks. However, the practical advantages of multi-agent collaboration approaches remain insufficiently understood. Existing evaluations often lack generalizability, failing to cover diverse tasks reflective of real-world clinical practice, and frequently omit rigorous comparisons against both single-LLM-based and established conventional methods. To address this critical gap, we introduce MedAgentBoard, a comprehensive benchmark for the systematic evaluation of multi-agent collaboration, single-LLM, and conventional approaches. MedAgentBoard encompasses four diverse medical task categories: (1) medical (visual) question answering, (2) lay summary generation, (3) structured Electronic Health Record (EHR) predictive modeling, and (4) clinical workflow automation, across text, medical images, and structured EHR data. Our extensive experiments reveal a nuanced landscape: while multi-agent collaboration demonstrates benefits in specific scenarios, such as enhancing task completeness in clinical workflow automation, it does not consistently outperform advanced single LLMs (e.g., in textual medical QA) or, critically, specialized conventional methods that generally maintain better performance in tasks like medical VQA and EHR-based prediction. MedAgentBoard offers a vital resource and actionable insights, emphasizing the necessity of a task-specific, evidence-based approach to selecting and developing AI solutions in medicine. It underscores that the inherent complexity and overhead of multi-agent collaboration must be carefully weighed against tangible performance gains. All code, datasets, detailed prompts, and experimental results are open-sourced at https://medagentboard.netlify.app/.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (yhzhu99/medagentboard) was not harvested; the 16 samples below come from 2 repositories the archive does not mark official.

Syntology 16 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 16 samples from 2 repositories, 11 ran (10 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yhzhu99/medagentboard officialmentioned in papermentioned on GitHubSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

16 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
10ran
5unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

HAIRLAB/Pre_Surv_COVID_19 found in paper text by Syntology 6 samples, 4 ran (0 instrument-failed) · 2 unverified
StratifiedKFold_func utils_features_selection.py ran MIT (permissive) · 90e6153dd6663fa7 · report fixture: signature x:ndarray/2/float, y:ndarray/1/int, Num_iter:int/0/int, model:XGBClassifier/0/?, score_type:str/0/str · returned list · level recorded 2026-09-25
StratifiedKFold_func_with_features_sel utils_features_selection.py ran MIT (permissive) · e9feaed780d7263b · report fixture: signature x:ndarray/2/float, y:ndarray/1/int, Num_iter:int/0/int, score_type:str/0/str · returned list · level recorded 2026-09-25
is_number in 70 papers utils.py ran fingerprinted MIT (permissive) · f97aabe235dec048 · report fixture: signature s:int/0/int · returned bool · level recorded 2026-09-25
merge_data_by_sliding_window utils.py ran MIT (permissive) · d8b6294050eecce3 · report fixture: signature data:DataFrame/0/?, n_days:int/0/int, dropna:bool/0/bool, subset:NoneType/0/?, time_form:str/0/str · returned DataFrame · level recorded 2026-09-25
read in 34 papers utils.py unverified MIT (permissive) · bd1a6c1715adc6c4 · report
read_train_data utils_features_selection.py unverified MIT (permissive) · eac7bc569b8add8a · report
huggingface/smolagents found in paper text by Syntology 10 samples, 7 ran (1 instrument-failed) · 3 unverified
get_dict_from_nested_dataclasses src/smolagents/models.py ran Apache-2.0 (permissive) · 990f6625f3b963da · report fixture: signature obj:OuterConfig/0/?, ignore_key:NoneType/0/? · returned dict · level recorded 2026-09-25
get_imports in 16 papers src/smolagents/_function_type_hints_utils.py ran fingerprinted Apache-2.0 (permissive) · 058f2cecb716999e · report fixture: signature code:str/0/str · returned list · level recorded 2026-09-25
get_package_name src/smolagents/_function_type_hints_utils.py ran fingerprinted Apache-2.0 (permissive) · 71f9eaf9b1c3790a · report fixture: signature import_name:str/0/str · returned str · level recorded 2026-09-25
nodunder_getattr src/smolagents/local_python_executor.py ran Apache-2.0 (permissive) · deb5a11caf7f2cf0 · report fixture: signature obj:SimpleObject/0/?, name:str/0/str, default:NoneType/0/? · returned str · level recorded 2026-09-25
parse_json_if_needed src/smolagents/models.py ran · our draft was wrong Apache-2.0 (permissive) · cfeb7cd7a490c27c · report fixture: signature arguments:dict/0/? · returned dict · level recorded 2026-09-24
populate_template src/smolagents/agents.py ran Apache-2.0 (permissive) · a5e997d9057b1af6 · report fixture: signature template:str/0/str, variables:dict/0/? · returned str · level recorded 2026-09-25
remove_content_after_stop_sequences src/smolagents/models.py ran Apache-2.0 (permissive) · 36443b04f5596ace · report fixture: signature content:str/0/str, stop_sequences:list/1/str · returned str · level recorded 2026-09-25
get_json_schema src/smolagents/_function_type_hints_utils.py unverified Apache-2.0 (permissive) · ad273f108393d5cf · report
handle_agent_output_types src/smolagents/agent_types.py unverified Apache-2.0 (permissive) · 608d577aef4c28b4 · report
safer_eval src/smolagents/local_python_executor.py unverified Apache-2.0 (permissive) · b51a3753b2d3d810 · report

Tasks

BenchmarkingMedical Visual Question AnsweringQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections