SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.07099 · EMNLP · 2024

Nash CoT: Multi-Path Inference with Preference Equilibrium

Ziqi Zhang, Yue Zhang, Donglin Wang, Cunxiang Wang, Xiao Xiong

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2407.07099.json · badge: /api/ran/2407.07099.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
amazon-science/auto-cot canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
FunctionStatusWhere it lives
shuffleDict Ran
ran; our contract draft was wrong, not the code
amazon-science/auto-cot/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from nku-hlt/role-play-prompting, is pointer only (licence: NONE) · get_code("ae2495a11361cc1d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from nku-hlt/role-play-prompting, and GitHub detected no licence in that repository 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.

decoder_for_gpt3 Not yet run
unverified (harvested, no recorded run)
amazon-science/auto-cot/utils.py
code served (permissive licence) · get_code("394a6c3347f3082a")
How it ran

no invocation recorded.

print_now Not yet run
unverified (harvested, no recorded run)
amazon-science/auto-cot/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from wjn1996/Chain-of-Knowledge, is pointer only (licence: NONE) · get_code("28145bbcf1d4f9ea")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from wjn1996/Chain-of-Knowledge, and GitHub detected no licence in that repository 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 0 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
print_now 10 other papers
7 dated earlier, 2 later, 1 same year, order not determinable
2210.03493 (2022-10)
Automatic Chain of Thought Prompting in Large Language Models
2305.13269 (2023-05)
Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
2308.07702 (2023-08)
Better Zero-Shot Reasoning with Role-Play Prompting
and 7 more not named here
shuffleDict 5 other papers
3 dated earlier, 1 later, 1 same year, order not determinable
2210.03493 (2022-10)
Automatic Chain of Thought Prompting in Large Language Models
2308.07702 (2023-08)
Better Zero-Shot Reasoning with Role-Play Prompting
2024.emnlp-main.758 (2024 (year only))
Fewer is More: Boosting Math Reasoning with Reinforced Context Pruning
and 2 more not named here
decoder_for_gpt3 1 other paper
1 dated earlier
2210.03493 (2022-10)
Automatic Chain of Thought Prompting in Large Language Models

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

Chain of thought (CoT) is a reasoning framework that can enhance the performance of Large Language Models (LLMs) on complex inference tasks. In particular, among various studies related to CoT, multi-path inference stands out as a simple yet effective improvement. However, there is no optimal setting for the number of inference paths. Therefore, we have to increase the number of inference paths to obtain better results, which in turn increases the inference cost. To address this limitation, we can utilize question-related role templates to guide LLMs into relevant roles, thereby increasing the possibility of correct inferences for each path and further reducing dependence on the number of inference paths while improving reasoning accuracy. However, placing LLMs into specific roles may reduce their reasoning diversity and performance on a few tasks where role dependence is low. To alleviate the excessive immersion of the LLM into a specific role, we propose Nash CoT by constructing a competitive system on each path that balances the generation from role-specific LLMs' and the general LLMs' generation, thereby ensuring both effective role adoption and diversity in LLM generation further maintaining the performance of multi-path inference while reducing the requirement of the number of inference paths. We evaluate Nash CoT across various inference tasks, including Arabic Reasoning, Commonsense Question Answering, and Symbolic Inference, achieving results that are comparable to or better than those of multi-path CoT with the equal number of inference paths.

For agents

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

get_harvested_code_for_paper("2407.07099")
get_code_for_paper("2407.07099")
have("2407.07099")

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

curl https://syntology.ai/api/ran/2407.07099.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.07099.svg)](https://syntology.ai/paper/2407.07099)

Connect an agent — have() is free.