SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.06307 · NeurIPS · 2025

Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks

Zhiwei Xu, Pengjie Ren, Zhaochun Ren, Zhumin Chen, Wentao Deng, Jiahuan Pei

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 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; 1 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 5 failures of our instrument; 4 no recorded run), measured 2026-11-22; 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/2510.06307.json · badge: /api/ran/2510.06307.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
dengwentao99/BCCS canonical (classifier label)
classifier basis: census
8 ran · 4 no recorded run
FunctionStatusWhere it lives
compare_numerical_ans Ran
ran, violated the contract we drafted
dengwentao99/BCCS/MATH/math_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("81082f28e1440f9d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

compute_accuracy Ran
ran, honoured the contract we drafted
dengwentao99/BCCS/MMLU/evaluate.py
pointer only (licence: NONE) · get_code("c8ac8a7c21aec637")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

construct_assistant_message Ran
ran; our contract draft was wrong, not the code
dengwentao99/BCCS/MATH/run_math.py
pointer only (licence: NONE) · get_code("9ae822b1cc802257")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

find_top_indices Ran
ran; our contract draft was wrong, not the code
dengwentao99/BCCS/MATH/run_math.py
pointer only (licence: NONE) · get_code("7da72e2c3ee47be7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

is_number Ran
ran, violated the contract we drafted
dengwentao99/BCCS/MATH/math_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("1c1060f6e43d5dfa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

lower_keys Ran
ran; our contract draft was wrong, not the code
dengwentao99/BCCS/MATH/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("0af0b06d6cf22524")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

parse_answer Ran
ran; our contract draft was wrong, not the code
dengwentao99/BCCS/MMLU/evaluate.py
pointer only (licence: NONE) · get_code("7548ef78c115707c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

solve_math_problems Ran
ran; our contract draft was wrong, not the code
dengwentao99/BCCS/MMLU/evaluate.py
pointer only (licence: NONE) · get_code("8fce0277228f26b2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

construct_message Not yet run
unverified (harvested, no recorded run)
dengwentao99/BCCS/MATH/run_math.py
pointer only (licence: NONE) · get_code("d1904765077ce803")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

extract_last_markdown_code_block Not yet run
unverified (harvested, no recorded run)
dengwentao99/BCCS/MATH/util.py
pointer only (licence: NONE) · get_code("706cde063018be8c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

extract_last_python_code_block Not yet run
unverified (harvested, no recorded run)
dengwentao99/BCCS/MATH/util.py
pointer only (licence: NONE) · get_code("40e3a4b4444ffb15")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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.

my_parse_latex Not yet run
unverified (harvested, no recorded run)
dengwentao99/BCCS/MATH/math_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from QwenLM/Qwen2.5-Math, is pointer only (licence: NONE) · get_code("73925940858a62b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dengwentao99/BCCS 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 4 later) and 7 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
compare_numerical_ans 6 other papers
5 dated earlier, 1 later
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2410.07985 (2024-10)
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
2504.05185 (2025-04)
Concise Reasoning via Reinforcement Learning
and 3 more not named here
is_number 6 other papers
5 dated earlier, 1 later
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2410.07985 (2024-10)
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
2504.05185 (2025-04)
Concise Reasoning via Reinforcement Learning
and 3 more not named here
my_parse_latex 6 other papers
5 dated earlier, 1 later
2405.14365 (2024-05)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
2410.07985 (2024-10)
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
2504.05185 (2025-04)
Concise Reasoning via Reinforcement Learning
and 3 more not named here
lower_keys 5 other papers
2 dated earlier, 1 the same month, 1 later, 1 undated
2309.17452 (2023-09)
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
2502.06773 (2025-02)
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
2510.20342 (2025-10)
Teaching Language Models to Reason with Tools
and 2 more not named here
solve_math_problems 2 other papers
2 dated earlier
2310.02170 (2023-10)
A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
2505.11765 (2025-05)
OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration

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 2026-11-22.

Repositories linked to this paper

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

Abstract

A multi-agent system (MAS) enhances its capacity to solve complex natural language processing (NLP) tasks through collaboration among multiple agents, where consensus-seeking serves as a fundamental mechanism. However, existing consensus-seeking approaches typically rely on voting mechanisms to judge consensus, overlooking contradictions in system-internal beliefs that destabilize the consensus. Moreover, these methods often involve agents updating their results through indiscriminate collaboration with every other agent. Such uniform interaction fails to identify the optimal collaborators for each agent, hindering the emergence of a stable consensus. To address these challenges, we provide a theoretical framework for selecting optimal collaborators that maximize consensus stability. Based on the theorems, we propose the Belief-Calibrated Consensus Seeking (BCCS) framework to facilitate stable consensus via selecting optimal collaborators and calibrating the consensus judgment by system-internal beliefs. Experimental results on the MATH and MMLU benchmark datasets demonstrate that the proposed BCCS framework outperforms the best existing results by 2.23% and 3.95% of accuracy on challenging tasks, respectively. Our code and data are available at https://github.com/dengwentao99/BCCS.

For agents

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

get_harvested_code_for_paper("2510.06307")
get_code_for_paper("2510.06307")
have("2510.06307")

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

curl https://syntology.ai/api/ran/2510.06307.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.06307.svg)](https://syntology.ai/paper/2510.06307)

Connect an agent — have() is free.