# ALIGN: Aligned Delegation with Performance Guarantees for Multi-Agent LLM Reasoning

Source: [ALIGN: Aligned Delegation with Performance Guarantees for Multi-Agent LLM Reasoning](<https://www.sota2.com/research/paper/69818127a8b01e76cc8e22f9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-04T05:00:04.388Z

Authors: Tong Zhu, Baiting Chen, Jin Zhou, Hua Zhou, Sriram Sankararaman, Xiaowu Dai

Published: 2026-01-28T00:29:21.000Z

## Abstract

LLMs often underperform on complex reasoning tasks when relying on a single generation-and-selection pipeline. Inference-time ensemble methods can improve performance by sampling diverse reasoning paths or aggregating multiple candidate answers, but they typically treat candidates independently and provide no formal guarantees that ensembling improves reasoning quality. We propose a novel method, Aligned Delegation for Multi-Agent LLM Reasoning (ALIGN), which formulates LLM reasoning as an aligned delegation game. In ALIGN, a principal delegates a task to multiple agents that generate candidate solutions under designed incentives, and then selects among their outputs to produce a final answer. This formulation induces structured interaction among agents while preserving alignment between agent and principal objectives. We establish theoretical guarantees showing that, under a fair comparison with equal access to candidate solutions, ALIGN provably improves expected performance over single-agent generation. Our analysis accommodates correlated candidate answers and relaxes independence assumptions that are commonly used in prior work. Empirical results across a broad range of LLM reasoning benchmarks consistently demonstrate that ALIGN outperforms strong single-agent and ensemble baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Mathematical Reasoning on GSM Hard (Accuracy)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm-hard-accuracy.md>): Mathematical Reasoning; GSM-Hard; Accuracy: 24.6.

- [Mathematical Reasoning on GSM8K (Accuracy %)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-accuracy-percent.md>): Mathematical Reasoning; GSM8K; Accuracy (GSM8K): 64.3.

- [Mathematical Reasoning on MATH (Accuracy and Token Usage)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math-accuracy-and-token-usage.md>): Mathematical Reasoning; MATH; Accuracy: 34.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.00127>)

[PDF](<https://arxiv.org/pdf/2602.00127.pdf>)