Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning
Identification
- Public canonical key
- radar:r-ea928fc66dca7aa299cfc93d3dacab84
- Authors
- Benjamin C Liu · Dillon Mehta · Rishi Malhotra · Adam Zobian · Yong Ying Tan · Samir Chopra · Daniella Rand · Natalie Pang · Abhiram Gudimella · Kevin Zhu
- Reported year
- 2026
- Reported language
- en
- Source type
- preprint
- First detected
- 2026-11-14T02:17:13.197093+00:00
- Last metadata observation
- 2026-11-14T02:17:13.197093+00:00
- Last HTTP verification
- Not checked
Institutions reported by the source
Stanford University · University of California San Diego · Rutgers, The State University of New Jersey · Foothill-De Anza Community College District · Fordham University · Chapman University · University of California, Berkeley
Reported affiliation countries
US
Documentary abstract — original language
Human interventions at fault points can alter the diagnostic accuracy of multi-agent medical systems. We defined fault points as moments in AI agent conversations, in which an agent's reasoning became most vulnerable to external influence. Using the MedQA dataset, this study analyzed simulated doctor-patient conversations to measure how interventions shifted reasoning and accuracy. Correct intervention methods showed an improvement in baseline diagnostic accuracy of up to 40%, while incorrect or bias-related interventions degraded performance by up to 6% and increased diagnostic drift and uncertainty. Beyond performance changes, our analysis revealed behavioral similarities between cognitive biases in simulated agent environments and real-world clinical practice. Examples included premature closure and susceptibility to misleading cues. Overall, these findings demonstrate that identifying and guiding fault points with human interventions may provide a mechanism for improving diagnostic robustness in multi-agent medical systems.
Identifiers
- OPENALEX
- https://openalex.org/W7207815226
- DOI
- 10.48550/arxiv.2609.02191
Documentary context
- Documentary family
- preprint
- Source-reported types
- preprint
Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.
Sources
OpenAlex · Record 1
Cite this reference
Benjamin C Liu; Dillon Mehta; Rishi Malhotra; Adam Zobian; Yong Ying Tan; Samir Chopra; Daniella Rand; Natalie Pang; Abhiram Gudimella; Kevin Zhu. Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning. 2026. https://doi.org/10.48550/arxiv.2609.02191
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690: bibliographic formats using available fields. OSCOLA / Bluebook: structured data only; full legal citation compliance is not claimed without verification of required elements.
- APA
- Benjamin C Liu; Dillon Mehta; Rishi Malhotra; Adam Zobian; Yong Ying Tan; Samir Chopra; Daniella Rand; Natalie Pang; Abhiram Gudimella; Kevin Zhu. (2026). Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning. https://doi.org/10.48550/arxiv.2609.02191
- Chicago
- Benjamin C Liu; Dillon Mehta; Rishi Malhotra; Adam Zobian; Yong Ying Tan; Samir Chopra; Daniella Rand; Natalie Pang; Abhiram Gudimella; Kevin Zhu. Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning. 2026. https://doi.org/10.48550/arxiv.2609.02191
- ISO 690
- Benjamin C Liu; Dillon Mehta; Rishi Malhotra; Adam Zobian; Yong Ying Tan; Samir Chopra; Daniella Rand; Natalie Pang; Abhiram Gudimella; Kevin Zhu. Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning. 2026. https://doi.org/10.48550/arxiv.2609.02191
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR Global Rights of Nature Legal Library. Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning. Documentary record: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-ea928fc66dca7aa299cfc93d3dacab84/ · Last HTTP verification: not performed
Research dossiers and documentary relations
Source roles
Bibliographic / original publication source · https://arxiv.org/abs/2609.02191
An authority link alone does not verify a legal claim. Abstracts and full texts remain subject to their source terms.
Documentary status
Relevance pending
Library
This identity is not yet included in the Legal Library.