The DOI matches its Crossref record; 84 of the 85 references it cites were found in a registry or an index; 6 of the 20 sources its claims cite were checked for support.
MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
Open accessAbstract
Large language models (LLMs), despite their remarkable progress across various general domains, encounter significant barriers in medicine and healthcare.This field faces unique challenges such as domain-specific terminologies and reasoning over specialized knowledge.To address these issues, we propose MEDAGENTS, a novel multi-disciplinary collaboration framework for the medical domain.MedAgents leverages LLM-based agents in a role-playing setting that participate in a collaborative multi-round discussion, thereby enhancing LLM proficiency and reasoning capabilities.This training-free framework encompasses five critical steps: gathering domain experts, proposing individual analyses, summarising these analyses into a report, iterating over discussions until a consensus is reached, and ultimately making a decision.Our work focuses on the zeroshot setting, which is applicable in realworld scenarios.Experimental results on nine datasets (MedQA, MedMCQA, PubMedQA, and six subtasks from MMLU) establish that our proposed MEDAGENTS framework excels at mining and harnessing the medical expertise within LLMs, as well as extending its reasoning abilities.Our code can be found at https: //github.com/gersteinlab/MedAgents.① Expert Gathering ② Analysis Proposition ③ Report Summarization ④ Collaborative Consultation ⑤ Decision Making A 66-year-old male with a history of heart attack and recurrent stomach ulcers is experiencing persistent cough and chest pain, and recent CT scans indicate a possible lung tumor.Designing a treatment plan that minimizes risk and maximizes outcomes is the current concern due to his deteriorating health and medical history....... ...... .
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
MedAgents is a training-free, multi-agent role-playing framework for zero-shot medical question answering that simulates multi-disciplinary expert consultation. Across nine medical datasets, it outperforms zero-shot baselines and approaches few-shot chain-of-thought/self-consistency baselines.
Key findings
- MedAgents achieved 64.1% on MedQA and 59.3% on MedMCQA with GPT-3.5, and 83.7% on MedQA and 74.8% on MedMCQA with GPT-4, outperforming zero-shot baselines and matching or approaching strong few-shot CoT+SC baselines.
- Ablation on MedQA showed gains from each stage: direct prompting 49.0%, CoT prompting 55.0%, +Analysis 62.0%, +Analysis & Summarization 65.0%, +Analysis & Summarization & Consultation 67.0%.
- Human error analysis of 40 randomly selected error cases in MedQA and MedMCQA found 77% of errors involved confusion about domain knowledge, while 8% were due to CoT errors.
- Agent quantity/domain variation mattered: on GPT-3.5, MedAgents with 6 different domains scored 64.1/59.3 on MedQA/MedMCQA, versus 59.2/58.1 with 6 same domains, 57.5/57.3 with 5 same domains, and 55.9/57.0 with 4 same domains.
Methods
- The framework has five stages: expert gathering, analysis proposition, report summarization, collaborative consultation, and decision making; experts vote and revise a report iteratively until consensus or a maximum attempt threshold.
- Experiments used GPT-3.5-Turbo and GPT-4 in zero-shot settings on nine datasets: MedQA, MedMCQA, PubMedQA, and six medical MMLU subtasks; 300 examples were randomly sampled per dataset.
- Generation settings included temperature 1.0 and top_p 1.0; question/option expert numbers were m=5, n=2 except PubMedQA m=4, n=2; maximum consultation attempts t=5; baselines included zero-shot, few-shot, CoT, and self-consistency prompting.
Limitations
- The paper states that parameterized LLM knowledge may need updating over time, that integrating diverse models at different stages could be explored, and that the framework may have limited applicability in low-resource languages.
- The paper reports cost and latency: about $1.41 per 100 QA examples and about 40 seconds inference time per example, which the authors acknowledge is more costly than CoT or direct prompting.
- The text makes evident a domain-knowledge bottleneck: 77% of analyzed errors related to lack or mis-retrieval of domain knowledge, and the domain variation study was conducted on only 20 samples due to manual evaluation.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
19 Own result · 16 Own interpretation · 4 Partly supported · 3 Sources not found · 2 No basis given · 1 No full text of the sources · 1 Not checked yet · 1 Own method · accuracy not yet measured
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“We have found that reliance on CoT in isolation can inadvertently result in hallucinations -spurious outputs typically associated with the misapplication of medical terminologies.”
- Also stated in: § A Analysis on the Addition of CoT · hedged
“As demonstrated in the example, for specialist domains that demand considerable expert knowledge such as the medical domain knowledge, employing a CoT approach might sometimes lead to hallucination (Bubeck et al., 2023;Guerreiro et al., 2023;Ji et al., 2023;Maynez et al., 2020).”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 3.2 Main Results
What the sources say
- Partly supportedcites Bubeck et al., 2023 sourceExperimental — accuracy not yet measured
Section 9.1 describes LLM hallucinations, and Section 10.2 warns that relying on hallucinated factual claims can be costly in healthcare. Figure 1.8 also shows a medical-note example containing claims not established by the patient's facts. The cited passages do not link those errors to reliance on CoT in isolation or characterize them as misapplied medical terminology. (LLM, conf=0.85)
- Partly supportedcites Guerreiro et al., 2023 sourceExperimental — accuracy not yet measured
Section 5.4 (p. 10) investigates hallucinations in medical-domain translation, supporting the general point that hallucinations can occur in that setting. It does not examine chain-of-thought (CoT) or attribute hallucinations to misapplied medical terminology. It also reports that hallucination rates were not consistently higher for medical data than for the comparison data. (LLM, conf=0.82)
- Not matchedcites Ji et al., 2023
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § A Analysis on the Addition of CoT · hedged
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“(ii) The demand for extensive domain knowledge (Schmidt and Rikers, 2007) and advanced reasoning skills (Liévin et al., 2022) makes eliciting medical expertise via simple prompting challenging (Kung et al., 2023;Singhal et al., 2023a).”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 1 Introduction
What the sources say
- Not checked — no full text of the sourcecites Schmidt and Rikers, 2007 source
- Supportedcites Liévin et al., 2022 source
The Liévin et al. citation is attached to “advanced reasoning skills,” not to the later claim about simple prompting. The Introduction (p. 2) says realistic medical questions require advanced reasoning capabilities, and Appendix C (p. 23) describes USMLE questions as requiring strong problem-solving skills. (LLM, conf=0.93)
- Partly supportedcites Kung et al., 2023 sourceExperimental — accuracy not yet measured
The Introduction describes USMLE questions as testing extensive medical knowledge and clinical reasoning, and the Results report that ChatGPT gave some inaccurate answers to questions posed as natural user queries. That supports the idea that eliciting reliable answers is challenging. But the Discussion (“The rising accuracy of ChatGPT”; page unavailable) says ChatGPT approached the passing range without prompt tuning or training, so the paper does not support the broader suggestion that simple prompting prevents LLMs from handling medical tasks effectively. (LLM, conf=0.78)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Such failures in medical question-answering originate from a lack of domain knowledge (Harris, 2023;Kung et al., 2023;Tian et al., 2024) instead of reasoning rationale.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > A Analysis on the Addition of CoT
What the sources say
- Not checked — no full text of the sourcecites Harris, 2023 source
- Partly supportedcites Kung et al., 2023 sourceExperimental — accuracy not yet measured
The Discussion (‘The rising accuracy of ChatGPT’; page unavailable) says inaccurate responses were driven primarily by missing information, supporting the domain-knowledge part of the claim. It does not establish that reasoning played no role: it also associates poorer accuracy with lower explanation concordance, and the Discussion (‘The potential for AI-assisted human learning in medical education’; page unavailable) says further failure-mode analysis is needed. (LLM, conf=0.88)
- Not matchedcites Tian et al., 2024
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“For example, the results from Liévin et al. (2022) demonstrate that CoT improvements are significantly limited.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > A Analysis on the Addition of CoT
What the sources say
- Partly supportedcites Liévin et al., 2022 sourceExperimental — accuracy not yet measured
The Discussion (p. 9) says single-sample CoT prompting was not competitive with direct prompting, supporting a limitation for that setting. But the Conclusion (p. 10) calls CoT a powerful tool that improved performance, and the Discussion (p. 10) reports gains from combining many CoTs. The unqualified claim that CoT improvements are significantly limited overstates the paper's finding. (LLM, conf=0.86)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We find that the optimal number of agents is relatively consistent across different datasets, pointing to its potential applicability to other datasets beyond those we test on.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 4.3 Number of agents
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Notably, our proposed MEDAGENTS framework outperforms the zero-shot baseline methods by a large margin, indicating the effectiveness of our MEDAGENTS framework in real-world application scenarios.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 3.2 Main Results
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: LLMs contain latent medical expertise that can be elicited through role-playing and multi-agent discussion.
- Rests on an assumption: The zero-shot setting is applicable in real-world scenarios.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Results in Table 6 depict minor variance for different sizes of data with random removing, reinforcing the notion that large-scale experiment performance remains largely robust against the effect of domain changes.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 4.4 Domain Variation Study
plainn = 20- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Results in Table 4 demonstrate that the open-source methods fell short of the baseline in Table 2, which leads us to focus on the more effective methods.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 4.2 Comparison with Open-source Medical Models
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our key observation lies in that the performance improves significantly with the introduction of any number of expert agents compared to our baseline, thus verifying the consistent contribution of multiple expert agents.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 4.3 Number of agents
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Most notably, our approach achieves better performance under the zero-shot setting compared with the 5-shot baselines.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 1 Introduction
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: The zero-shot setting is applicable in real-world scenarios.
- It may state two separate claims as one. 8
- Probably not a substantial claim. 6
- The quote only partly states this claim. 4
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Results in Table 3 show that all of these processes are non-trivial.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 4.1 Ablation Study
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Encouragingly, our proposed approach outperforms settings for both chain-of-thought (CoT) and self-consistency (SC) prompting methods.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 1 Introduction
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: LLMs contain latent medical expertise that can be elicited through role-playing and multi-agent discussion.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In our extensive examination of the MEDAGENTS framework, we discover the decent correctional capabilities of our framework.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 4.7 Correctional Capabilities and Interpretability
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“*zero-shot setting Zero-shot Zero-shot CoT Zero-shot CoT + SC 61.3 54.3 44.3 MedAgents (Ours) 64.1 | 56.3 47.3 52.5 59.3 | 73.7 61.3 75.7 72.9 | 61.5 63.7 71.1 65.2 | | 76.2 61.9 75.1 77.7 | 63.6 53.2 68.8 69.8 | 74.0 66.0 76.0 79.0 | 75.4 62.1 82.3 82.1 | 75.0 67.8 65.3 58.3 75.7 70.9 78.5 72.1 |”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Vote Result:
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“*zero-shot setting Zero-shot Zero-shot CoT Zero-shot CoT + SC 74.5 73.0 61.8 MedAgents (Ours) 83.7 | 69.0 69.0 70.1 74.8 | 76.2 71.0 75.3 76.8 | 78.5 82.1 80.0 83.5 | | 83.3 85.2 86.3 91.0 | 75.6 80.8 81.2 87.6 | 90.0 92.0 93.0 93.0 | 90.0 93.5 94.8 96.0 | 90.0 80.6 91.7 80.8 91.7 83.0 94.3 86.7 |”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Vote Result:
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“MC framework GPT-4 (5 repetitions) 83.5 74.9”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Additional information
plainn = 300- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“*zero-shot setting Zero-shot Zero-shot CoT Zero-shot CoT + SC 74.5 73.0 61.8 MedAgents (Ours) 83.7 | 69.0 69.0 70.1 74.8 | 76.2 71.0 75.3 76.8 | 78.5 82.1 80.0 83.5 | | 83.3 85.2 86.3 91.0 | 75.6 80.8 81.2 87.6 | 90.0 92.0 93.0 93.0 | 90.0 93.5 94.8 96.0 | 90.0 80.6 91.7 80.8 91.7 83.0 94.3 86.7 |”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Vote Result:
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“*zero-shot setting Zero-shot Zero-shot CoT Zero-shot CoT + SC 61.3 54.3 44.3 MedAgents (Ours) 64.1 | 56.3 47.3 52.5 59.3 | 73.7 61.3 75.7 72.9 | 61.5 63.7 71.1 65.2 | | 76.2 61.9 75.1 77.7 | 63.6 53.2 68.8 69.8 | 74.0 66.0 76.0 79.0 | 75.4 62.1 82.3 82.1 | 75.0 67.8 65.3 58.3 75.7 70.9 78.5 72.1 |”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Vote Result:
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This iterative refinement serves as a practical demonstration of our model's proficiency in rectifying errors, substantiating its interpretability and accuracy in complex medical reasoning tasks.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 4.7 Correctional Capabilities and Interpretability
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: A unanimous report generated by iterative expert consultation best represents the collective expert knowledge and reasoning on the given medical problem.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Different medical professionals offer depth and breadth in the analysis, transforming it into a comprehensive assessment.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Additional information
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Unlike these methods, our work emphasizes harnessing latent medical knowledge intrinsic to LLMs and improving reasoning in a training-free setting.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Example Interpretation
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
- Rests on an assumption: LLMs contain latent medical expertise that can be elicited through role-playing and multi-agent discussion.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“In essence, the key to LLM-based multi-agent collaboration is the simulation of human activities such as role-playing (Wang et al., 2023d;Hong et al., 2023) and communication (Wu et al., 2023a;Qian et al., 2023;Li et al., 2023b,c).”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 5.2 LLM-based Multi-agent Collaboration
What the sources say
- Not matchedcites Wang et al., 2023d
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites Hong et al., 2023
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites Wu et al., 2023a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Not matched
In the paper
“Although Med-PaLM (Singhal et al., 2023b) serves as a specialized medical LLM fine-tuned on the basis of PaLM 2, it is closed-sourced and not publicly accessible yet.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Vote Result:
What the sources say
- Not matchedcites Singhal et al., 2023b
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The process of selecting these domains is automated via prompting, and our manual inspection confirms the high relevance and quality of the selected domains.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > 4.5 Agent Quantity Study
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Experimental results on nine datasets (MedQA, MedMCQA, PubMedQA, and six subtasks from MMLU) establish that our proposed MEDAGENTS framework excels at mining and harnessing the medical expertise within LLMs, as well as extending its reasoning abilities.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Abstract
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: LLMs contain latent medical expertise that can be elicited through role-playing and multi-agent discussion.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“MedAgents leverages LLM-based agents in a role-playing setting that participate in a collaborative multi-round discussion, thereby enhancing LLM proficiency and reasoning capabilities.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: LLMs contain latent medical expertise that can be elicited through role-playing and multi-agent discussion.
The paper relies on this without support.
LLMs contain latent medical expertise that can be elicited through role-playing and multi-agent discussion.
“Through such design, the expertise implicitly embedded within LLMs, or that the model has encountered during its training, which may not be readily accessible via traditional prompting, is effectively brought to the fore.”
The paper relies on this without support.
The zero-shot setting is applicable in real-world scenarios.
“Our work focuses on the zeroshot setting, which is applicable in realworld scenarios.”
The paper relies on this without support.
The multi-disciplinary consultation mechanism is common and effective in hospitals.
“Inspired by the multi-disciplinary consultation mechanism which is common and effective in hospitals, we are thus inspired to apply this mechanism to medical reasoning tasks through LLM-based multi-agent collaboration.”
The paper relies on this without support.
The authors are the first to propose a multi-agent framework within the medical domain.
“(i) To the best of our knowledge, we are the first to propose a multi-agent framework within the medical domain and explore how multi-agent communication within the medical setting can lead to a consensus decision, adding a novel dimension to the current literature on medical question answering.”
The paper relies on this without support.
A unanimous report generated by iterative expert consultation best represents the collective expert knowledge and reasoning on the given medical problem.
“Ultimately, after iterative refinement and consultation, a unanimous report is generated that best represents the collective expert knowledge and reasoning on the given medical problem.”
The paper relies on this without support.
The assembled LLM experts possess respective disciplinary backgrounds.
“The assembled LLM experts, possessing respective disciplinary backgrounds, engage in a discussion over the initial report, voicing agreements and disagreements.”
The paper relies on this without support.
An initial report synthesizing the analyses concisely represents the performed evaluations.
“An initial report synthesizing these analyses is then prepared to concisely represent the performed evaluations.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source doesn’t support the claim as written.
In the citing paper
“MedAgents32 emphasizes QA improvement through agent collaboration but does not simulate patient interactions or decision-making processes.”
From AgentClinic: a multimodal benchmark for tool-using clinical AI agents (2026) · cites this paper as [32]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Coding agents have also been applied to offensive security [11, 37, 60], theorem proving [44], and clinical tasks [38, 43, 52].”
From SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering (2024) · cites this paper as [43]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Recent advancements in multi-agent systems have shown promising results in medical decision-making and diagnosis.”
From Enhancing diagnostic capability with multi-agents conversational large language models (2025) · cites this paper as [25]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Current studies on multi-agent architectures have largely emphasized their enhanced text understanding capabilities, particularly in generative tasks62–65.”
From MoMA: a mixture-of-multimodal-agents architecture for enhancing clinical prediction modelling (2025) · cites this paper as [64]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“For example, MEDAGENTS is an innovative multi-disciplinary collaboration framework that enhances large language models’ performance in zero-shot medical question answering25.”
From Enhancing diagnostic capability with multi-agents conversational large language models (2025) · cites this paper as [25]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“However, they have yet to demonstrate whether such architectures can effectively leverage their text understanding abilities to improve prediction performance in classification tasks involving multimodal EHR data, which is a critical need in clinical applications.”
From MoMA: a mixture-of-multimodal-agents architecture for enhancing clinical prediction modelling (2025) · cites this paper as [64]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Vote Result:
“The final report suggested Tympanometry as the best medication for the patient's condition.”
§ MEDAGENTS: Large Language Models as Collaborators for Zero-shot Medical Reasoning > Question: Eustachian tube function is best assessed by: (A) Tympanometry (B) VEMP (C) Rhinomanometry (D) Politzer tests
“Question: Eustachian tube function is best assessed by: (A) Tympanometry (B) VEMP (C) Rhinomanometry (D) Politzer tests”
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083
Large language models in medicine
Thirunavukarasu, A. J., Ting, D. S. J., Elangovan, K., Gutierrez, L., Tan, T. F., & Ting, D. S. W. (2023) · Nature Medicine · doi:10.1038/s41591-023-02448-8 · Cited by 3,944
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187
Foundation models for generalist medical artificial intelligence
Moor, M., Banerjee, O., Abad, Z. S. H., Krumholz, H. M., Leskovec, J., Topol, E. J., & Rajpurkar, P. (2023) · Nature · doi:10.1038/s41586-023-05881-4 · Cited by 2,028
Research works printed but not linked: 3
- Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12):1-38.
- PMLR.
- PMLR.
Cited by
Sorted by citations
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
Self-citationA Comprehensive Overview of Large Language Models
Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N., & Mian, A. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3744746 · Cited by 1,257
The Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972
The rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970
A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges
Li, X., Wang, S., Zeng, S., Wu, Y., & Yang, Y. (2024) · Vicinagearth · doi:10.1007/s44336-024-00009-2 · Cited by 404
AgentClinic: a multimodal benchmark for tool-using clinical AI agents
Schmidgall, S., Ziaei, R., Harris, C., Kim, J. W., Reis, E. P., Jopling, J., & Moor, M. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02674-7 · Cited by 344
Empowering biomedical discovery with AI agents
Gao, S., Fang, A., Huang, Y., Giunchiglia, V., Noori, A., Schwarz, J. R., Ektefaie, Y., Kondic, J., & Zitnik, M. (2024) · Cell · doi:10.1016/j.cell.2024.09.022 · Cited by 315
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Yang, J., Jimenez, C., Wettig, A., Lieret, K., Yao, S., Narasimhan, K., & Press, O. (2024) · Advances in Neural Information Processing Systems 37 · doi:10.52202/079017-1601 · Cited by 264
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.00352 · Cited by 214
LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language ModelsPreprint
Zhang, Y., Mao, S., Ge, T., Wang, X., de Wynter, A., Xia, Y., Wu, W., Song, T., Lan, M., & Wei, F. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.01230 · Cited by 186
Zhao, S., Yang, Y., Wang, Z., He, Z., Qiu, L. K., & Qiu, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.14924 · Cited by 179
From Matching to Generation: A Survey on Generative Information Retrieval
Li, X., Jin, J., Zhou, Y., Zhang, Y., Zhang, P., Zhu, Y., & Dou, Z. (2025) · ACM Transactions on Information Systems · doi:10.1145/3722552 · Cited by 172
Foundation Model for Advancing Healthcare: Challenges, Opportunities and Future Directions
He, Y., Huang, F., Jiang, X., Nie, Y., Wang, M., Wang, J., & Chen, H. (2024) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2024.3496744 · Cited by 162
FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language ModelsPreprint
Yang, H., Zhang, B., Wang, N., Guo, C., Zhang, X., Lin, L., Wang, J., Zhou, T., Guan, M., Zhang, R., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4841493 · Cited by 158
Self-citationA comprehensive survey of large language models and multimodal large language models in medicine
Xiao, H., Zhou, F., Liu, X., Liu, T., Ли, Ж., Liu, X., & Huang, X. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102888 · Cited by 154
Enhancing diagnostic capability with multi-agents conversational large language models
Chen, X., Yi, H., You, M., Liu, W., Wang, L., Li, H., Zhang, X., Guo, Y., Fan, L., Chen, G., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01550-0 · Cited by 147
Self-citationA Survey of LLM-based Agents in Medicine: How far are we from Baymax?
Wang, W., Ma, Z., Wang, Z., Chenghan, W., Ji, J., Chen, W., Li, X., & Yuan, Y. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.539 · Cited by 144
Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent SystemsPreprint
Yan, B., Zhou, Z., Zhang, L., Zhang, L., Zhou, Z., Miao, D., Li, C., Li, C., & Zhang, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.14321 · Cited by 143
Self-citationChain of Agents: Large Language Models Collaborating on Long-Context Tasks
Zhang, Y., Sun, R., Chen, Y., Pfister, T., Zhang, R., & Arık, S. Ö. (2024) · neural information processing systems · doi:10.52202/079017-4202 · Cited by 138
KG-RAG: Bridging the Gap Between Knowledge and CreativityPreprint
Sanmartin, D. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.12035 · Cited by 138
Mou, X., Ding, X., He, Q., Wang, L., Liang, J., Zhang, X., Sun, L., Lin, J., Zhou, J., Huang, X., et al. (2026) · ACM Computing Surveys · doi:10.1145/3800683 · Cited by 130
Self-citationLLMs and generative agent-based models for complex systems research
Lu, Y., Aleta, A., Du, C., Shi, L., & Moreno, Y. (2024) · Physics of Life Reviews · doi:10.1016/j.plrev.2024.10.013 · Cited by 107
How to Bridge the Gap Between Modalities: Survey on Multimodal Large Language Model
Song, S., Li, X., Li, S., Zhao, S., Yu, J., Ma, J., Mao, X., Zhang, W., & Wang, M. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3527978 · Cited by 105
Flooding spread of manipulated knowledge in LLM-based multi-agent communities
Ju, T., Wang, Y., Hua, Y., Ma, X., Cheng, P., Zhao, H., Wang, Y., Liu, L., Xie, J., Zhang, Z., et al. (2026) · Science China Information Sciences · doi:10.1007/s11432-024-4663-2 · Cited by 102
Self-citationRed-Teaming LLM Multi-Agent Systems via Communication Attacks
He, P., Lin, Y., Dong, S., Xu, H., Xing, Y., & Liu, H. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.349 · Cited by 98
Wei, T., Li, T.-W., Liu, Z., Ning, X., Yang, Z., Zou, J., Zeng, Z., Qiu, R., Lin, X., Fu, D., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.12538 · Cited by 97
Self-citationImproving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions
Xiong, G., Jin, Q., Wang, X., Zhang, M., Lu, Z., & Zhang, A. (2024) · Pacific Symposium on Biocomputing (PSB) · doi:10.1142/9789819807024_0015 · Cited by 91
ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning
Wan, Z., Li, Y., Wen, X., Song, Y., Wang, H., Yang, L., Schmidt, M., Wang, J., Zhang, W., Hu, S., et al. (2025) · neural information processing systems · doi:10.52202/085713-4225 · Cited by 91
Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization
Tseng, Y.-M., Huang, Y.-C., Hsiao, T.-Y., Chen, W.-L., Huang, C.-W., Meng, Y., & Chen, Y.-N. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.969 · Cited by 87
AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator
Fan, Z., Tang, J., Chen, W., Wang, S., Wei, Z., Xi, J., Huang, F., & Zhou, J. (2024) · arXiv · doi:10.48550/arxiv.2402.09742 · Cited by 84
Large Language Model based Multi-Agents: A Survey of Progress and Challenges
Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., Wiest, O., & Zhang, X. (2024) · arXiv · doi:10.48550/arxiv.2402.01680 · Cited by 1,713
Self-citationMathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics EducationPreprint
Yue, M., Lyu, W., Suh, J., Zhang, Y., & Yao, Z. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.06711 · Cited by 68
Healthcare agent: eliciting the power of large language models for medical consultation
Ren, Z., Zhan, Y., Yu, B., Ding, L., Xu, P., & Tao, D. (2025) · npj Artificial Intelligence · doi:10.1038/s44387-025-00021-x · Cited by 67
From intention to implementation: automating biomedical research via LLMs
Luo, Y., Shi, L., Li, Y., Zhuang, A., Gong, Y., Liu, L., & Chen, L. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4485-0 · Cited by 67
AgentMD: Empowering language agents for risk prediction with large-scale clinical tool learning
Jin, Q., Wang, Z., Yang, Y., Zhu, Q., Wright, D., Huang, T. Y., Khandekar, N., Wan, N., Ai, X., Wilbur, W. J., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-64430-x · Cited by 66
MMedAgent: Learning to Use Medical Tools with Multi-modal Agent
Li, B., Yan, T., Pan, Y., Luo, J., Ji, R., Ding, J., Xu, Z., Liu, S., Dong, H., Lin, Z., et al. (2024) · arXiv · doi:10.48550/arxiv.2407.02483 · Cited by 65
VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge
Nath, V., Li, W., Yang, D., Myronenko, A., Zheng, M., Lu, Y., Liu, Z., Yin, H., Law, Y. M., Tang, Y., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01378 · Cited by 64
NetSafe: Exploring the Topological Safety of Multi-agent NetworksPreprint
Yu, M., Wang, S., Zhang, G., Mao, J., Yin, C., Liu, Q., Wen, Q., Wang, K., & Wang, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.15686 · Cited by 64
How Far Are We From AGI: Are LLMs All We Need?Preprint
Feng, T., Jin, C., Liu, J., Zhu, K., Tu, H., Cheng, Z., Lin, G., & You, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.10313 · Cited by 62
LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models
Yang, H., Chen, H. M., Hui, G., Chen, Y., Lin, C.-S., Hu, S., Hu, J., Wu, X., & Wang, X. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228647 · Cited by 58
Li, R., Wang, X., Berlowitz, D. R., Mez, J., Lin, H., & Yu, H. Z. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01940-4 · Cited by 57
Towards generalizable AI in medicine via Generalist–Specialist Collaboration
He, S., Nie, Y., Wang, H., Yang, S., Wang, Y., Cai, Z., Chen, Z., Xu, Y., Wu, L., Cheng, N. S., et al. (2026) · Nature Biomedical Engineering · doi:10.1038/s41551-026-01653-3 · Cited by 56
MMedAgent: Learning to Use Medical Tools with Multi-modal Agent
Li, B., Yan, T., Pan, Y., Luo, J., Ji, R., Ding, J., Xu, Z., Liu, S., Dong, H., Lin, Z., et al. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.510 · Cited by 54
MEDCO: Medical Education Copilots Based on a Multi-agent Framework
Wei, H., Qiu, J., Yu, H., & Yuan, W. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91813-1_8 · Cited by 53
From Intention To Implementation: Automating Biomedical Research via LLMs
Luo, Y., Shi, L., Li, Y., Zhuang, A., Gong, Y., Liu, L., & Lin, C. (2024) · arXiv · doi:10.48550/arxiv.2412.09429 · Cited by 53
The anatomy of a personal health agent
Heydari, A. A., Gu, K., Srinivas, V., Yu, H., Paruchuri, A., Zhang, Z., Zhang, Y., He, Q., Palangi, H., Hammerquist, N., et al. (2026) · Nature · doi:10.48550/arxiv.2508.20148 · Cited by 52
Self-citationLiu, Y., Lo, S. K., Lu, Q., Zhu, L., Zhao, D., Xu, X., Harrer, S., & Whittle, J. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2024.112278 · Cited by 51
Gu, Z., Chen, J., Liu, F., Yin, C., & Zhang, P. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500255 · Cited by 51
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Mangaokar, N., Hooda, A., Choi, J., Chandrashekaran, S., Fawaz, K., Jha, S., & Prakash, A. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.591 · Cited by 51
AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent CollaborationPreprint
Pan, B., Lu, J., Wang, K., Li, Z., Wen, Z., Feng, Y., Zhu, M., & Chen, W. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.11943 · Cited by 51
Self-citationMulti-Agent Collaboration via Cross-Team OrchestrationPreprint
Du, Z., Qian, C., Liu, W., Xie, Z., Wang, Y., Qiu, R., Dang, Y., Chen, W., Yang, C. H., Tian, Y., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.08979 · Cited by 49
Large language model agents can use tools to perform clinical calculations
Goodell, A. J., Chu, S. N., Rouholiman, D., & Chu, L. F. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01475-8 · Cited by 48
Chen, K., Li, X., Yang, T., Wang, H., Dong, W., & Gao, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.13856 · Cited by 47
Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents
Li, J., Lai, Y., Li, W., Ren, J., Zhang, M., Kang, X., Wang, S., Li, P., Zhang, Y.-Q., Ma, W., et al. (2024) · arXiv · doi:10.48550/arxiv.2405.02957 · Cited by 46
MedChain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence
Liu, J., Wang, W., Ma, Z., Huang, G., Yihang, S., Chang, K.-J., Li, H., Shen, L., Lyu, M. R.-T., & Chen, W. (2025) · neural information processing systems · doi:10.52202/085713-2498 · Cited by 44
Simulating Financial Market via Large Language Model based AgentsPreprint
Gao, S., Wen, Y., Zhu, M., Wei, J., Cheng, Y., Zhang, Q., & Shang, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.19966 · Cited by 44
Wang, Z., Zhu, Y., Zhao, H., Zheng, X., Sui, D., Wang, T., Tang, W., Wang, Y., Harrison, E. M., Pan, C., et al. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714877 · Cited by 43
MedAide: Information fusion and anatomy of medical intents via LLM-based agent collaboration
Yang, D., Wei, J., Li, M., Liu, J., Liu, L., Hu, M., He, J., Ju, Y., Zhou, W., Liu, Y., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103743 · Cited by 41
A comprehensive survey of AI agents in healthcare
Xu, G., Li, X., Chen, Y., Duan, Y., Wu, S., Yu, H., Chiu, C.-H., Ni, J., Tang, N., Li, T. J.-J., et al. (2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.105045 · Cited by 41
AI agent in healthcare: applications, evaluations, and future directions
Zhao, L., Liu, S., Xin, T., Tan, J., Wang, X., Li, Y., Bian, Z., Chen, Y., Kong, F., Bian, J., et al. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00076-4 · Cited by 38
Self-citationLu, Q., Zhu, L., Xu, X., Xing, Z., Harrer, S., & Whittle, J. (2024) · IEEE International Conference on Software Architecture Companion (ICSA-C) · doi:10.1109/icsa-c63560.2024.00028 · Cited by 38
RDguru: A Conversational Intelligent Agent for Rare Diseases
Yang, J., Shu, L., Duan, H., & Li, H. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3464555 · Cited by 37
Multi-agent systems for chemical engineering: a review and perspective
Rupprecht, S., Gao, Q., Karia, T., & Schweidtmann, A. M. (2025) · Current Opinion in Chemical Engineering · doi:10.1016/j.coche.2025.101209 · Cited by 37
Learning to break: Knowledge-enhanced reasoning in multi-agent debate system
Wang, H., Du, X., Yu, W., Chen, Q., Zhu, K., Chu, Z., Yan, L., & Guan, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2024.129063 · Cited by 36
SurgRAW: Multi-Agent Workflow With Chain of Thought Reasoning for Robotic Surgical Video Analysis
Low, C. H., Wang, Z., Zhang, T., Zhuo, Z., Zeng, Z., Mazomenos, E. B., & Jin, Y. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3665443 · Cited by 32
Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and PhysicsPreprint
Zhou, L., Ling, H., Fu, C., Huang, Y., Sun, M., Yu, W., Wang, X., Li, X., Su, X., Zhang, J., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.09901 · Cited by 32
Giacobbe, D. R., Marelli, C., Manna, B. L., Padua, D., Malva, A., Guastavino, S., Signori, A., Mora, S., Rosso, N., Campi, C., et al. (2025) · npj Antimicrobials and Resistance · doi:10.1038/s44259-025-00084-5 · Cited by 31
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Yang, J., Jimenez, C. E., Wettig, A., Lieret, K., Yao, S., Narasimhan, K., & Press, O. (2024) · arXiv · doi:10.48550/arxiv.2405.15793 · Cited by 31
Wei, L., Wang, W., Shen, X., Xie, Y., Fan, Z., Zhang, X., Wei, Z., & Chen, W. R. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.04521 · Cited by 31
Self-citationKGARevion: An AI Agent for Knowledge-Intensive Biomedical QAPreprint
Su, X., Wang, Y., Gao, S., Liu, X., Giunchiglia, V., Clevert, D.-A., & Žitnik, M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.04660 · Cited by 30
Agentic AI and the rise of in silico team science in biomedical research
Li, B., Saini, A. K., Hernandez, J. G., & Moore, J. H. (2026) · Nature Biotechnology · doi:10.1038/s41587-026-03035-1 · Cited by 29
OpenFOAMGPT 2.0: End-to-end, trustworthy automation for computational fluid dynamics
Feng, J., Xu, R., & Chu, X. (2026) · International Journal of Heat and Fluid Flow · doi:10.1016/j.ijheatfluidflow.2026.110399 · Cited by 29
Multimodal integration strategies for clinical application in oncology
Zhang, B., Wan, Z., Luo, Y., Zhao, X., Samayoa, J. A., Zhao, W., & Wu, S. (2025) · Frontiers in Pharmacology · doi:10.3389/fphar.2025.1609079 · Cited by 28
Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question AnsweringPreprint
Wu, F., Li, Z., Wei, F., Li, Y., Ding, B., & Gao, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.07813 · Cited by 28
Self-citationAgentCoord: Visually exploring coordination strategy for LLM-based multi-agent collaboration
Pan, B., Lu, J., Wang, K., Li, Z., Wen, Z., Feng, Y., Zhu, M., & Chen, W. (2025) · Computers & Graphics · doi:10.1016/j.cag.2025.104338 · Cited by 27
Self-citationVatsal, S., Dubey, H., & Singh, A. (2026) · IEEE Access · doi:10.1109/access.2026.3651218 · Cited by 27
Yang, T., Xiao, Y., Bao, Z., Hao, J., & Peng, J. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf601 · Cited by 27
Wang, G., Gao, M., Yang, S., Ya, Z., He, L., Huang, L., Xiao, H., Zhang, Y., Li, W., Chen, L., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.18274 · Cited by 27
Large Language Models in Medical Image Analysis: A Systematic Survey and Future Directions
Urooj, B., Fayaz, M., Ali, S., Dang, L. M., & Kim, K. W. (2025) · Bioengineering · doi:10.3390/bioengineering12080818 · Cited by 26
Multi-Agent Collaboration Mechanisms: A Survey of LLMs
Tran, K.-T., Dao, D., Nguyen, M.-D., Pham, Q.-V., O'Sullivan, B., & Nguyen, H. D. (2025) · arXiv · doi:10.48550/arxiv.2501.06322 · Cited by 680
Yue, L., Somasekharan, N., Zhang, T., Cao, Y., & Pan, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.18178 · Cited by 26
Visual–language foundation models in medicine
Liu, C., Jin, Y., Guan, Z., Li, T., Qin, Y., Qian, B., Jiang, Z., Wu, Y.-L., Wang, X., Zheng, Y. F., et al. (2024) · The Visual Computer · doi:10.1007/s00371-024-03579-w · Cited by 25
Evolving Interactive Diagnostic Agents in a Virtual Clinical EnvironmentPreprint
Qiu, P., Wu, C., Liu, J., Zheng, Q., Liao, Y., Wang, H., Yue, Y., Fan, Q., Zhen, S., Wang, J., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.24654 · Cited by 25
Feng, Y., Wang, J., He, R., Zhou, L., & Li, Y. (2025) · GigaScience · doi:10.1093/gigascience/giaf109 · Cited by 24
Medical Dialogue System: A Survey of Categories, Methods, Evaluation and Challenges
Shi, X., Liu, Z., Du, L., Wang, Y., Wang, H., Guo, Y., Ruan, T., Xu, J., Zhang, X., & Zhang, S. (2024) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2024.findings-acl.167 · Cited by 24
Self-citationA Multimodal Multi-agent Framework for Radiology Report Generation
Yi, Z., Liu, J., Xiao, T., & Albert, M. V. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-22190-2_11 · Cited by 24
Chen, L., Zhang, Y., Feng, J., Chai, H., Zhang, H., Fan, B., Ma, Y., Zhang, S., Li, N., Liu, T., et al. (2026) · Humanities and Social Sciences Communications · doi:10.1057/s41599-026-07316-7 · Cited by 23
DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models
Wang, B., Chang, J., Qian, Y., Chen, G., Chen, J., Jiang, Z., Zhang, J., Nakashima, Y., & Nagahara, H. (2024) · neural information processing systems · doi:10.52202/079017-2386 · Cited by 23
MeNTi: Bridging Medical Calculator and LLM Agent with Nested Tool Calling
Zhu, Y., Wei, S., Wang, X., Xue, K., Zhang, S., & Zhang, X. (2025) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2025.naacl-long.263 · Cited by 22
Self-citationEnhancing LLMs for Impression Generation in Radiology Reports through a Multi-Agent SystemPreprint
Zeng, F., Lyu, Z., Li, Q., & Li, X. R. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.06828 · Cited by 22
WSI-Agents: A Collaborative Multi-Agent System for Multi-Modal Whole Slide Image AnalysisPreprint
Lyu, X., Liang, Y., Chen, W., Ding, M., Yang, J., Huang, G., Zhang, D., He, X., & Shen, L. (2025) · arXiv (Cornell University) · Cited by 22
ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemes
Hong, S., Xiao, L., Zhang, X., & Chen, J. (2024) · 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822109 · Cited by 21
Self-citationLarge language model for medical images: a survey of taxonomy, systematic review, and future trends
Wang, P., Lu, W., Lu, C., Zhou, R., Li, M., & Qin, L. (2025) · Big Data Mining and Analytics · doi:10.26599/bdma.2024.9020090 · Cited by 21
Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical ScenariosPreprint
Xu, S., Zhou, Y., Liu, Z., Wu, Z., Zhong, T., Zhao, H., Li, Y., Jiang, H., Pan, Y., Chen, J., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.14461 · Cited by 21
Applications and Future Prospects of Medical LLMs: A Survey Based on the M-KAT Conceptual Framework
Chang, Y., Yin, J., Li, J., Liu, C., Cao, L., & Lin, S. (2024) · Journal of Medical Systems · doi:10.1007/s10916-024-02132-5 · Cited by 20
Xu, X., & Sankar, R. (2025) · Information · doi:10.3390/info16100894 · Cited by 20
YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language ModelsPreprint
Wang, L., Gao, H. O., Bo, X., Chen, X., & Wen, J.-R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.07581 · Cited by 20
Multi-level Value Alignment in Agentic AI Systems: Survey and PerspectivesPreprint
Zeng, W., Zhu, H., Qin, C., Wu, H., Cheng, Y., Zhang, S., Jin, X., Shen, Y., Wang, Z., Zhong, F., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.09656 · Cited by 20
Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective
Gabison, G. A., & Xian, R. P. (2025) · Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025) · doi:10.18653/v1/2025.realm-1.9 · Cited by 19
HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare ResearchPreprint
Zhu, Y., Qi, Y., Wang, Z., Gu, L., Sui, D., Hu, H., Zhang, X., He, Z., He, J., Ma, L., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.02621 · Cited by 19
Self-citation
Metadata
- Authors
- Tang, X., Zou, A., Zhang, Z., Li, Z., Zhao, Y., Zhang, X., Cohan, A., & Gerstein, M.
- Affiliations
- Shanghai Jiao Tong University (CN)
- Venue
- Findings of the Association for Computational Linguistics ACL 2024
- Published
- 2024
- Pages
- 599-621
- OpenAlex
- W4402670791
- Cited by
- 376
- References
- 33
- Citations by year
- 2026: 156 · 2025: 157 · 2024: 62
- FWCI
- 79.79
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: ACL (Findings of ACL) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- large language models, LLM agents, role-playing agents, training-free framework, medical question answering, expert consultation, decision-making
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-07, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-07 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
