Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

EMS: Multi-Agent Voting via Efficient Majority-then-Stopping

Yiqing Liu, Hantao Yao, Wu Liu, Yongdong Zhang

Abstract

Majority voting is the standard for aggregating multi-agent responses into a final decision. However, traditional methods typically require all agents to complete their reasoning before aggregation begins, leading to significant computational overhead, as many responses become redundant once a majority consensus is achieved. In this work, we formulate the multi-agent voting as a reliability-aware agent scheduling problem, and propose an Efficient Majority-then-Stopping (EMS) to improve reasoning efficiency. EMS prioritizes agents based on task-aware reliability and terminates the reasoning pipeline the moment a majority is achieved from the following three critical components. Specifically, we introduce Agent Confidence Modeling (ACM) to estimate agent reliability using historical performance and semantic similarity, Adaptive Incremental Voting (AIV) to sequentially select agents with early stopping, and Individual Confidence Updating (ICU) to dynamically update the reliability of each contributing agent. Extensive evaluations across six benchmarks demonstrate that EMS consistently reduces the average number of invoked agents by 32%.

EMS: Multi-Agent Voting via Efficient Majority-then-Stopping

Abstract

Majority voting is the standard for aggregating multi-agent responses into a final decision. However, traditional methods typically require all agents to complete their reasoning before aggregation begins, leading to significant computational overhead, as many responses become redundant once a majority consensus is achieved. In this work, we formulate the multi-agent voting as a reliability-aware agent scheduling problem, and propose an Efficient Majority-then-Stopping (EMS) to improve reasoning efficiency. EMS prioritizes agents based on task-aware reliability and terminates the reasoning pipeline the moment a majority is achieved from the following three critical components. Specifically, we introduce Agent Confidence Modeling (ACM) to estimate agent reliability using historical performance and semantic similarity, Adaptive Incremental Voting (AIV) to sequentially select agents with early stopping, and Individual Confidence Updating (ICU) to dynamically update the reliability of each contributing agent. Extensive evaluations across six benchmarks demonstrate that EMS consistently reduces the average number of invoked agents by 32%.

Paper Structure

This paper contains 19 sections, 17 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Multi-Agent Systems.
  4. Efficient Multi-Agent Inference.
  5. Multi-Agent Voting and Aggregation.
  6. Methodology
  7. Problem Formulation
  8. Agent Confidence Modeling
  9. Adaptive Incremental Voting
  10. Individual Confidence Updating
  11. Experiments
  12. Experimental Setup
  13. Main Results
  14. Ablation Study
  15. Effect of Early Stopping.
  16. ...and 4 more sections

Figures (3)

  • Figure 1: Intuitive comparison of different multi-agent voting processes. There exists a significant difference in terms of Number of Invoked Agents among different voting sequences.
  • Figure 2: Overview of the proposed Efficient Majority-then-Stopping (EMS) framework. For each query, EMS first uses the Agent Confidence Modeling (ACM) to determine a reliability-aware voting order. It then performs incremental voting via Adaptive Incremental Voting (AIV), where agents are invoked sequentially according to the estimated order. Finally, Individual Confidence Updating (ICU) updates the confidence state of the agents contributing to the majority-voting.
  • Figure 3: Analysis of the Adaptive Incremental Voting. Each bar represents the proportion of questions that achieve the final results based on the "Agents Invoked".