SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2508.17536 · NeurIPS · 2025

Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?

Sharon Li, Hyeong Kyu, Choi Zhu

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 3 no recorded run), measured 2026-11-21; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2508.17536.json · badge: /api/ran/2508.17536.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
deeplearning-wisc/debate-or-vote canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
FunctionStatusWhere it lives
engine Ran
ran; our contract draft was wrong, not the code
deeplearning-wisc/debate-or-vote/src/model/model_utils.py
pointer only (licence: NONE) · get_code("250845e8d32fd7f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deeplearning-wisc/debate-or-vote when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate_arithmetics Ran
ran; our contract draft was wrong, not the code
deeplearning-wisc/debate-or-vote/src/evaluator.py
pointer only (licence: NONE) · get_code("a72d68a37728a783")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deeplearning-wisc/debate-or-vote when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate_mcq Ran
ran; our contract draft was wrong, not the code
deeplearning-wisc/debate-or-vote/src/evaluator.py
pointer only (licence: NONE) · get_code("073596ca49ad3ad6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deeplearning-wisc/debate-or-vote when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gather_last_token Ran
ran; our contract draft was wrong, not the code
deeplearning-wisc/debate-or-vote/src/model/llama.py
pointer only (licence: NONE) · get_code("8dfbcae9b1f4de30")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deeplearning-wisc/debate-or-vote when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_agents Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
deeplearning-wisc/debate-or-vote/src/model/model_utils.py
pointer only (licence: NONE) · get_code("e0d0218eb20a3f0c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deeplearning-wisc/debate-or-vote when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_instruction_suffix Ran
ran; our contract draft was wrong, not the code
deeplearning-wisc/debate-or-vote/src/evaluator.py
pointer only (licence: NONE) · get_code("ec5050de1f9e05c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deeplearning-wisc/debate-or-vote when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_zero_shot_prompt Not yet run
unverified (harvested, no recorded run)
deeplearning-wisc/debate-or-vote/src/model/llama.py
pointer only (licence: NONE) · get_code("b7f8ce776f3eb615")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deeplearning-wisc/debate-or-vote when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
deeplearning-wisc/debate-or-vote/src/model/llama.py
pointer only (licence: NONE) · get_code("d37a4d52cbb58ff4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deeplearning-wisc/debate-or-vote when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
deeplearning-wisc/debate-or-vote/src/model/qwen.py
pointer only (licence: NONE) · get_code("5eac478ca93897a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deeplearning-wisc/debate-or-vote when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
create_zero_shot_prompt 1 other paper
1 later
2603.20640 (2026-03)
Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention
evaluate_arithmetics 1 other paper
1 later
2603.20640 (2026-03)
Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention
evaluate_mcq 1 other paper
1 later
2603.20640 (2026-03)
Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention
gather_last_token 1 other paper
1 later
2603.20640 (2026-03)
Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention
get_instruction_suffix 1 other paper
1 later
2603.20640 (2026-03)
Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Multi-Agent Debate (MAD) has emerged as a promising paradigm for improving the performance of large language models through collaborative reasoning. Despite recent advances, the key factors driving MAD's effectiveness remain unclear. In this work, we disentangle MAD into two key components-Majority Voting and inter-agent Debate-and assess their respective contributions. Through extensive experiments across seven NLP benchmarks, we find that Majority Voting alone accounts for most of the performance gains typically attributed to MAD. To explain this, we propose a theoretical framework that models debate as a stochastic process. We prove that it induces a martingale over agents' belief trajectories, implying that debate alone does not improve expected correctness. Guided by these insights, we demonstrate that targeted interventions, by biasing the belief update toward correction, can meaningfully enhance debate effectiveness. Overall, our findings suggest that while MAD has potential, simple ensembling methods remain strong and more reliable alternatives in many practical settings. Code is released in https://github.com/deeplearning-wisc/debate-or-vote.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2508.17536")
get_code_for_paper("2508.17536")
have("2508.17536")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2508.17536.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2508.17536.svg)](https://syntology.ai/paper/2508.17536)

Connect an agent — have() is free.