Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Simple ensembling methods (majority voting) may account for most of the performance gains initially attributed to complex agent interactions.
“In fact, simple ensembling methods (majority voting) may account for most of the performance gains initially attributed to complex agent interactions [66].”
From A Review of Multi-Agent AI Systems for Biological and Clinical Data Analysis (2026) · cites this paper as [66]
No citation lists for this paper
No citation lists for this paper yet — checked again daily.
Cited by 6
- Authors
- Choi, H. K., Zhu, J., & Li, S.
- Affiliations
- University of Wisconsin–Madison (US)
- Carnegie Mellon University (US)
- Venue
- Advances in Neural Information Processing Systems 38
- Published
- 2025
- Pages
- 112802-112834
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7196961442
- Cited by
- 6
- References
- 0
- Citations by year
- 2026: 6
- FWCI
- 5.72
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- neural information processing systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Game Theory and Voting Systems
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Keywords
- debate, voting, multi-agent systems, large language models, decision-making, multi-agent debate
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.
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
