Does Multi-Agent Collaboration Reduce Hallucination in Clinical Tasks?

2026-10-22 12:00 arXiv cs.AI Won Seok Jang, Harry Bhaskar Joshi, Hong Yu 约 11 分钟读完

Multi-agent LLM systems improve performance on clinical tasks, and that improvement is often read as evidence of a more trustworthy system. However, the two are not the same claim. A clinician acts on the stated reasoning and not only on the conclusion, so whether collaboration reduces hallucination…

Authors: Won Seok Jang , Harry Bhaskar Joshi , Hong Yu

View a PDF of the paper titled Does Multi-Agent Collaboration Reduce Hallucination in Clinical Tasks?, by Won Seok Jang and 2 other authors

View PDF

HTML (experimental)

Abstract: Multi-agent LLM systems improve performance on clinical tasks, and that improvement is often read as evidence of a more trustworthy system. However, the two are not the same claim. A clinician acts on the stated reasoning and not only on the conclusion, so whether collaboration reduces hallucination, and what decides when it does, has to be measured in the reasoning too. Yet most evaluations score only the final answer. We evaluate four systems (a single-LLM baseline and three multi-agent topologies) across four models and three clinical tasks, scoring hallucination, under a factuality and faithfulness taxonomy, inside the rationale each system generates and reporting it alongside the task metric. We report that collaboration buys task performance but not lower hallucination as a rule, and no topology is reliably better than another. The effect differs by model: of the $36$ model--system--task comparisons, $12$ are large enough to resolve --- four decreases and eight increases, with no model on both sides. What sets the level, and the direction of any change, is the model rather than the topology or the number of agents. A self-correction experiment is consistent with this: shown its own flagged errors, every model except Llama-3.2-3B-Instruct reduces hallucination; the one model for which collaboration lowers hallucination gains the most, and Llama-3.2-3B-Instruct, the model whose hallucination it amplifies most, does not reduce its hallucination at all. We find that collaboration redistributes what its models can already do; it does not supply what they cannot.

Subjects:

Artificial Intelligence (cs.AI)

Cite as:

arXiv:2610.27027 [cs.AI]

(or

arXiv:2610.27027v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2610.27027

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Won Seok Jang [ view email ]

[v1]

Mon, 19 Oct 2026 15:08:17 UTC (244 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Does Multi-Agent Collaboration Reduce Hallucination in Clinical Tasks?, by Won Seok Jang and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

< prev

next >

new

recent

| 2026-10

Change to browse by:

References & Citations

SciX

Google Scholar

Semantic Scholar

export BibTeX citation

BibTeX formatted citation

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer ( What is the Explorer? )

Connected Papers Toggle

Connected Papers ( What is Connected Papers? )

Litmaps Toggle

Litmaps ( What is Litmaps? )

scite.ai Toggle

scite Smart Citations ( What are Smart Citations? )

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv ( What is alphaXiv? )

Links to Code Toggle

CatalyzeX Code Finder for Papers ( What is CatalyzeX? )

DagsHub Toggle

DagsHub ( What is DagsHub? )

GotitPub Toggle

Gotit.pub ( What is GotitPub? )

Huggingface Toggle

Hugging Face ( What is Huggingface? )

ScienceCast Toggle

ScienceCast ( What is ScienceCast? )

Demos

Replicate Toggle

Replicate ( What is Replicate? )

Spaces Toggle

Hugging Face Spaces ( What is Spaces? )

Spaces Toggle

TXYZ.AI ( What is TXYZ.AI? )