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
Items 101–200 of 410
Mejia, J. M. R., & Rawat, D. B. (2025) · Healthcare · doi:10.3390/healthcare13141649 · Cited by 18
Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions
Gridach, M., Nanavati, J., Abidine, K. Z. E., Mendes, L., & Mack, C. (2025) · arXiv · doi:10.48550/arxiv.2503.08979 · Cited by 18
Planning and Editing What You Retrieve for Enhanced Tool Learning
Huang, T., Jung, D., Kumar, V., Kachuee, M., Li, X., Xu, P., & Chen, M. (2024) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2024.findings-naacl.61 · Cited by 18
Tzanis, E., & Klontzas, M. E. (2025) · European Journal of Radiology Artificial Intelligence · doi:10.1016/j.ejrai.2025.100044 · Cited by 17
A multi-agent framework with legal event logic graph for multi-defendant legal judgment prediction
Yuan, W., Song, K., Jiang, Z., Cao, J., Zhang, Y., Liu, C., Lin, J., Zhang, J., Kuang, K., & Liu, X. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104319 · Cited by 17
To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent SystemsPreprint
He, P., Dai, Z., Tang, X., Xing, Y., Liu, H., Zeng, J., Peng, Q., Agrawal, S., Varshney, S., Wang, S., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.02546 · Cited by 17
Self-citationAltermatt, F. R., Neyem, A., Sumonte, N. I., Mendoza, M., Villagrán, I., & Lacassie, H. J. (2025) · BMC Medical Education · doi:10.1186/s12909-025-07250-3 · Cited by 16
Hong, S., Cai, C., Du, S., Feng, H., Liu, S., & Fan, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98462-4_4 · Cited by 16
SurgBox: Agent-Driven Operating Room Sandbox with Surgery Copilot
Wu, J., Liang, X., Bai, X., & Chen, Z. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825748 · Cited by 15
OpenHands: An Open Platform for AI Software Developers as Generalist Agents
Wang, X., Li, B., Song, Y., Xu, F. F., Tang, X., Zhuge, M., Pan, J., Song, Y., Li, B., Singh, J., et al. (2024) · arXiv · doi:10.48550/arxiv.2407.16741 · Cited by 24
Self-citationLi, H., Cheng, X., & Xiao-ping, Z. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713526 · Cited by 15
AgentDiagnose: An Open Toolkit for Diagnosing LLM Agent Trajectories
Ou, T., Guo, W., Gandhi, A., Neubig, G., & Xiang, Y. (2025) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/2025.emnlp-demos.15 · Cited by 15
DAWN: Designing Distributed Agents in a Worldwide Network
Aminiranjbar, Z., Tang, J., Wang, Q., Pant, S., & Viswanathan, M. (2025) · IEEE Access · doi:10.1109/access.2025.3588425 · Cited by 15
Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement LearningPreprint
Lai, Y., Liu, K., Wang, Z., Ma, W., & Liu, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.04284 · Cited by 15
Reviewing clinical knowledge in medical large language models: Training and beyond
Li, Q. Y., Liu, H., Guo, C., Gao, C., Chen, D., Wang, M., Gao, F., van Harmelen, F., & Gu, J. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114215 · Cited by 14
Owais, M., Zubair, M., Kareem, D. N. A., Naseer, S. A., Alam, M., Ahmad, M., & Hussain, I. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10738-w · Cited by 14
BioKGBench: A Knowledge Graph Checking Benchmark of AI Agent for Biomedical SciencePreprint
Lin, X., Ma, S., Shan, J., Zhang, X., Hu, S. X., Guo, T., Li, S. Z., & Yu, K. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.00466 · Cited by 14
Self-citationWang, S., Zhao, F., Bu, D., Lu, Y., Gong, M., Liu, H., Yang, Z., Zeng, X., Yuan, Z., Wan, B., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-64142-2 · Cited by 13
Self-citationNetSafe: Exploring the Topological Safety of Multi-agent System
Yu, M., Wang, S., Zhang, G., Mao, J., Yin, C., Liu, Q., Wang, K., Wen, Q., & Wang, Y. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.150 · Cited by 13
Mushtaq, A., Naeem, R., Taj, I., Ghaznavi, I., & Qadir, J. (2025) · IEEE Global Engineering Education Conference (EDUCON) · doi:10.1109/educon62633.2025.11016405 · Cited by 13
Exploring the Inquiry-Diagnosis Relationship with Advanced Patient SimulatorsPreprint
Liu, Z., Tu, Q., Ye, W., Xiao, Y., Zhang, Z., Cui, H., Zhu, Y., Ju, Q., Li, S., & Xie, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.09484 · Cited by 13
Self-citationComprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MASPreprint
He, P., Xing, Y., Li, J., Dong, S., Dai, Z., Tang, X., Liu, H., Xu, H., Xiang, Z., Aggarwal, C. C., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.01245 · Cited by 13
Self-citationBeyond Chatbots: Moving Toward Multistep Modular AI Agents in Medical Education
Chow, M., & Ng, O. (2025) · JMIR Medical Education · doi:10.2196/76661 · Cited by 12
A Systematic Literature Review of Artificial Intelligence in Prehospital Emergency Care
Elfahim, O., Edjinedja, K. L., Cossus, J., Youssfi, M., Barakat, O., & Desmettre, T. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9090219 · Cited by 12
Project Sid: Many-agent simulations toward AI civilization
AL, A., Ahn, A., Becker, N., Carroll, S., Christie, N., Cortes, M., Demirci, A., Du, M., Li, F., Luo, S., et al. (2024) · arXiv · doi:10.48550/arxiv.2411.00114 · Cited by 12
Advancing Collaborative Debates with Role Differentiation through Multi-Agent Reinforcement Learning
Li, H., Su, Z., Xue, Y., Tian, Z., Song, Y., & Huang, M. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-long.1105 · Cited by 12
Zhao, L., Bian, Z., Chen, Q., Li, Y., Luo, Z., Bai, J., Li, G., He, M., Li, K., Yao, H., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.21418 · Cited by 12
Self-citationMedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision
Zheng, H., Shi, Z., & Yi, P. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356820 · Cited by 11
Su, M., Liu, C., Zhang, J., Shuang, W., & Fan, M. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754593 · Cited by 11
Step-Back Profiling: Distilling User History for Personalized Scientific WritingPreprint
Tang, X., Zhang, X., Shao, Y., Wu, J., Zhao, Y., Cohan, A., Gong, M., Zhang, D., & Gerstein, M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.14275 · Cited by 11
Self-citationLiu, B., Nie, Y., Song, H., Lin, Y., Li, J., Weng, X., Su, Z., Suo, Y., Lv, T., Zhao, X., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103557 · Cited by 10
Wu, H., Boulenger, P., Faure, A., Céspedes, B., Boukil, F., Morel, N., Chen, Z., & Bosselut, A. (2024) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2024.bionlp-1.61 · Cited by 10
Huang, G., Chen, W., Yang, J., Lyu, X., Luo, X., Yang, S., Xing, X., & Shen, L. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835399 · Cited by 10
MRGAgents: A Multi-Agent Framework for Improved Medical Report Generation with Med-LVLMs
Wang, P., Ye, S., Naseem, U., & Kim, J. (2025) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta68720.2025.11302496 · Cited by 10
Akinseloyin, O., Jiang, X., & Palade, V. (2026) · Biology Methods and Protocols · doi:10.1093/biomethods/bpag006 · Cited by 10
KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent SystemsPreprint
Zhang, J., Huang, Z., Fan, Y., Liu, N., Li, M., Yang, Z., Yao, J., Wang, J., & Wang, K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.07350 · Cited by 10
ENTAgents: AI Agents for Complex Knowledge Otolaryngology
Chan, T. K., & Dinh, N.-D. (2025) · doi:10.1101/2025.01.01.25319863 · Cited by 9
Al-Jebrni, A. H., Jiang, Z., Qin, Y., Qiu, Y., Jiang, N., Li, G., Zheng, Y., Wong, T. Y., Kim, S., Jung, Y., et al. (2026) · Computational Visual Media · doi:10.26599/cvm.2026.9450530 · Cited by 9
Tree-of-Reasoning: Towards Complex Medical Diagnosis via Multi-Agent Reasoning with Evidence Tree
Peng, Q., Cui, J., Xie, J., Cai, Y., & Li, Q. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755418 · Cited by 9
Shi, H., Zhang, J., & Zhang, K. (2026) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi69079.2026.00111 · Cited by 9
The AI Agent in the Room: Informing Objective Decision Making at the Transplant Selection Committee
Hasjim, B. J., Azafar, G., Lee, F. G., Diwan, T. S., Raju, S., Gross, J. A., Sidhu, A., Ichii, H., Krishnan, R. G., Mamdani, M., et al. (2025) · American Journal of Transplantation · doi:10.1016/j.ajt.2025.07.2270 · Cited by 9
Autonomous Droplet Microfluidic Design Framework with Large Language Models
Nguyen, D.-N., Tong, R. K., & Dinh, N. (2025) · ACS Omega · doi:10.1021/acsomega.5c06253 · Cited by 9
Generative AI for healthcare: fundamentals, challenges, and perspectives
Chen, G., Liu, C., Anne, O. G., Tan, M., Xie, Z., Yin, J., Yip, J. W. L., Zhang, W., ZHU, J., & Ooi, B. C. (2026) · Science China Information Sciences · doi:10.1007/s11432-025-4927-2 · Cited by 9
“Tipping the Balance”: Human Intervention in Large Language Model Multi‐Agent Debate
Triem, H., & Ding, Y. (2024) · Proceedings of the Association for Information Science and Technology · doi:10.1002/pra2.1034 · Cited by 9
Advanced machine learning techniques for social support detection on social media
Kolesnikova, O., Tash, M. S., Ahani, Z., Agrawal, A., Monroy, R., & Sidorov, G. (2025) · Heliyon · doi:10.1016/j.heliyon.2025.e43437 · Cited by 9
Position: Foundation Agents as the Paradigm Shift for Decision MakingPreprint
Liu, X., Lou, X., Jiao, J., & Zhang, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.17009 · Cited by 9
MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language ModelsPreprint
Ma, S., Huang, J., Zhang, F., Shen, Y., Wu, J., Fan, G., Zhang, Z., & Zang, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.23725 · Cited by 9
Self-citationLiu, H., Zhu, Y., Wang, Y., Long, Y., Lai, Z., Yu, L., & Chen, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.24314 · Cited by 9
Gu, B., Zhou, H., Segal, B., Wu, J., Cao, Z., Zhong, H., Clifton, L., Liu, F., & Clifton, D. A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.00601 · Cited by 9
A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answering
Yi, Z., Liu, J., Albert, M. V., & Xiao, T. (2025) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1109/jcdl67857.2025.00025 · Cited by 8
Large language models in healthcare and biomedical informatics: A comprehensive review
Hornback, A. M., Sathu, H., Kim, K., Wang, Y., Zhu, Y., Isgut, M., Avula, P., Khimani, A., & Wang, M. D. (2026) · Innovation and Emerging Technologies · doi:10.1142/s2737599426300011 · Cited by 8
Lyu, X., Liang, Y., Chen, W., Ding, M., Yang, J., Huang, G., Zhang, D., He, X., & Shen, L. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04971-1_64 · Cited by 8
Multi-agent Reasoning for Cardiovascular Imaging Phenotype Analysis
Zhang, W., Qiao, M., Zang, C., Niederer, S., Matthews, P. M., Bai, W., & Kainz, B. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04927-8_41 · Cited by 8
DAWN: Designing Distributed Agents in a Worldwide Network
Aminiranjbar, Z., Tang, J., Wang, Q., Pant, S., & Viswanathan, M. (2024) · arXiv · doi:10.48550/arxiv.2410.22339 · Cited by 8
Scaling Large Language Model-based Multi-Agent Collaboration
Qian, C., Xie, Z., Wang, Y., Liu, W., Zhu, K., Xia, H., Dang, Y., Du, Z., Chen, W., Yang, C., et al. (2024) · arXiv · doi:10.48550/arxiv.2406.07155 · Cited by 8
Agentic AI in Healthcare: Opportunities, Challenges, and Future Directions
Gridach, M., Nanavati, J., Zine El Abidine, K., Yacoubian, C., & Mack, C. (2026) · ACM Computing Surveys · doi:10.1145/3809164 · Cited by 8
Multi-Agent Collaboration via Cross-Team Orchestration
Du, Z. Z., Chen, Q., Liu, W., Xie, Z., Wang, Y., Qiu, R., Dang, Y., Chen, W., Yang, C., Tian, Y., et al. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.541 · Cited by 8
CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation
Lou, J., Yang, Y. Q., Zhou, Y., Fu, Z., Han, W., Huang, Q., & Yu, J. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3713585 · Cited by 8
DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making
Shang, T., He, W., Zheng, C., Li, L., Shen, L., & Zhao, B. (2025) · PubMed · doi:10.48550/arxiv.2507.02616 · Cited by 8
Ju, T., Wang, B., Fei, H., Lee, M. L., Hsu, W., Li, Y., Wang, Q., Cheng, P., Wu, Z., Zhao, H., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.15153 · Cited by 8
Self-citationLiu, C., Chen, W.-Y., Xu, H., Du, Y., Yang, J. T., & Du, L. (2025) · International Symposium of Electronics Design Automation (ISEDA) · doi:10.1109/iseda65950.2025.11101698 · Cited by 7
Tang, J., Wu, N., Gao, F., Dai, C., Zhao, M., & Zhao, X. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228098 · Cited by 7
EpidemIQs: Prompt-to-Paper LLM Agents for Epidemic Modeling and Analysis
Samaei, M. H., Sahneh, F. D., Cohnstaedt, L. W., & Scoglio, C. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3666830 · Cited by 7
Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
Ren, S., Xie, C., Jian, P., Ren, Z., Leng, C., & Zhang, J. (2025) · arXiv · doi:10.48550/arxiv.2503.24047 · Cited by 7
Tzanis, E., & Klontzas, M. E. (2026) · Radiology Artificial Intelligence · doi:10.1148/ryai.250923 · Cited by 7
AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering
Wang, Z., Mao, C., Wen, X., Luo, Y., & Ding, K. (2025) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2025.findings-emnlp.1350 · Cited by 7
Sikkander, A. R. M., Rodrigues, J. J. P. C., Meena, M., & Abuelmakarem, H. S. (2025) · World Journal of Applied Medical Sciences · doi:10.65336/wjams.2025.21205 · Cited by 7
Document-level Clinical Entity and Relation extraction via Knowledge Base-Guided Generation
Bhattarai, K., Oh, I. Y., Abrams, Z. B., & Lai, A. M. (2024) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2024.bionlp-1.24 · Cited by 7
Pinard, C. J., Poon, A. C., Lagree, A., Wu, K., Li, J., & Tran, W. T. (2024) · Veterinary and Comparative Oncology · doi:10.1111/vco.13035 · Cited by 7
Qu, Z., Yin, L., Yu, Z., Wang, W., & Zhang, X. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.04781 · Cited by 7
Self-citationIMAS: A Comprehensive Agentic Approach to Rural Healthcare DeliveryPreprint
Gangavarapu, A., & Gangavarapu, A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.12868 · Cited by 7
Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent CollaborationPreprint
Wang, J., Zhao, S., Wang, H., Fan, Y., & Liu, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.02200 · Cited by 7
A Self-Evolving Framework for Multi-Agent Medical Consultation Based on Large Language Models
Chen, K., Qi, J., Huo, J., Tian, P., Meng, F., Yang, X., & Gao, Y. (2025) · ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49660.2025.10889517 · Cited by 6
Reasoning LLMs in the Medical Domain: A Literature Survey
Berger, A., Khanna, S., Sparrenberg, L., Deußer, T., Berghaus, D., & Sifa, R. (2025) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa65442.2025.11247922 · Cited by 6
A study on multi-modal LLM reasoning for defect detection
Tulbure, A. A., Danciu, D.-P., Dulf, E. H., & Tulbure, A. A. (2024) · IEEE International Symposium for Design and Technology in Electronic Packaging (SIITME) · doi:10.1109/siitme63973.2024.10814831 · Cited by 6
SmokeAgent: Multimodal agent for fine-grained smoke event analysis in large-scale wild environments
Cao, Y., Yang, F., Li, X., & Lu, X. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111765 · Cited by 6
Choi, J., Palumbo, N., Chalasani, P., Engelhard, M. M., Jha, S., Kumar, A., & Page, D. (2024) · arXiv · doi:10.48550/arxiv.2408.01869 · Cited by 6
TAKAGI, H., Moriya, S., Sato, T., Nagao, M., & Higuchi, K. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708359.3712119 · Cited by 6
M3MAD-Bench: Multi-Dimensional Evaluation of Multi-Agent Debate Across Domains and Modalities
Li, A., Zhang, J., Li, L., Duan, Y., Gao, L., Chen, M., Qin, W., Li, S., Ji, F., Liu, N., et al. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835372 · Cited by 6
Huang, J., He, R., Khan, D. Z., Mazomenos, E. B., Stoyanov, D. V., Marcus, H. J., Jiang, L., Clarkson, M. J., & Islam, M. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i3.37164 · Cited by 6
QUB-Cirdan at “Discharge Me!”: Zero shot discharge letter generation by open-source LLM
Guo, R., Farnan, G., McLaughlin, N., & Devereux, B. J. (2024) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2024.bionlp-1.58 · Cited by 6
SwiftDossier: Tailored Automatic Dossier for Drug Discovery with LLMs and AgentsPreprint
Fossi, G., Boulaimen, Y., Outemzabet, L., Jeanray, N., Gérart, S., Vachenc, S., Giemza, J., & Raieli, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.15817 · Cited by 6
MMFactory: A Universal Solution Search Engine for Vision-Language TasksPreprint
Fan, W.-C., Rahman, T., & Sigal, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.18072 · Cited by 6
Ultrasound-QBench: Can LLMs Aid in Quality Assessment of Ultrasound Imaging?Preprint
Miao, H., Jia, J., Cao, Y., Zhou, Y., Jiang, Y., Liu, Z., & Zhai, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.02751 · Cited by 6
Wang, Y., Yan, Q., Xing, Z.-H., Liu, L., He, J., Fu, C., Hu, X., & Heng, P.-A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.21503 · Cited by 6
Mediator-Guided Multi-Agent Collaboration among Open-Source Models for Medical Decision-MakingPreprint
Chen, K., Liu, M., Zong, D., Ding, C., Rui, S., Jiang, Y., Zhou, M., & Wang, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.05996 · Cited by 6
The AI Agent in the Room: Informing Objective Decision Making at the Transplant Selection CommitteePreprint
Hasjim, B. J., Azarfar, G., Lee, F. G., et al. (2024) · medRxiv · doi:10.1101/2024.12.06.24318575 · Cited by 5
Medical Reasoning With Large Language Models: A Systematic Review and Evaluation
Ren, X., Fan, C., Ma, W., He, H., Gao, C., Zhao, X., & Feng, F. (2026) · iNew Medicine · doi:10.1002/inm3.70056 · Cited by 5
Digital psychiatry: concepts, framework, and implications
Wu, H., & Li, M. D. (2025) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2025.1572444 · Cited by 5
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Luo, J., Zhang, W., Yuan, Y., Zhao, Y., Yang, J., Gu, Y., Wu, B., Chen, B., Qiao, Z., Long, Q., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.21460 · Cited by 5
Self-citationInoue, Y., Song, T., Wang, X., Kuang, R., Fu, T., & Luna, A. (2024) · arXiv · doi:10.48550/arxiv.2408.13378 · Cited by 5
Sun, Y., Yue, W., Jin, X., Ma, S., Ma, X., & Wang, X. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757705 · Cited by 5
eSkinHealth: A Multimodal Dataset for Neglected Tropical Skin Diseases
Wang, J., Hu, X., Zhang, Y., Almamy, D., Vagamon, B., Koffi, K. A. S., Yao, K. A., Ding, Z., Hamm, J., & Yotsu, R. R. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758241 · Cited by 5
OPGAgent: An Agent for Auditable Dental Panoramic X-Ray Interpretation
Yu, Z., Yang, L., Babicka, B., Hu, M., Hao, J., Huang, A., Huang, J., Jin, Y., Wu, J., & Ge, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38062-3_43 · Cited by 5
MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Models
Ma, S., Huang, J., Zhang, F., Wu, J., Shen, Y., Fan, G., Zhang, Z., & Zang, Z. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i2.37052 · Cited by 5
Self-citationA Holistic Review of Agentic AI Frameworks, Applications, and Research Trajectories
Peykani, P., Ghanidel, S., Javadi-Sisi, I., Snåšel, V., & Mirjalili, S. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10675-8 · Cited by 5
Chen, T. Y., Yao, H., Chen, J., Papalexakis, E. E., & Wei, H. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.737 · Cited by 5
Chen, J., Yang, H., Liu, Z., & Joe-Wong, C. (2025) · doi:10.36227/techrxiv.175760290.08279849/v1 · Cited by 5
Stochastic Self-Organization in Multi-Agent SystemsPreprint
Tastan, N., Horváth, S., & Nandakumar, K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.00685 · Cited by 5
A Survey of LLM-based Multi-agent Systems in MedicinePreprint
Lin, Y., Xu, S., Zhang, W., Sun, Y., Chen, Z., Zhang, Y., & Sheng, R. (2025) · Preprints.org · doi:10.20944/preprints202510.1448.v1 · Cited by 5
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
