AgentCDM: Enhancing Multi-Agent Collaborative Decision-Making via ACH-Inspired Structured Reasoning

TL;DR

AgentCDM introduces a structured, ACH-inspired reasoning framework for multi-agent systems using LLMs, significantly improving collaborative decision-making by reducing biases and enhancing robustness and generalization.

Contribution

This work presents a novel ACH-inspired structured reasoning paradigm and a two-stage training process for LLM-based multi-agent systems, advancing beyond existing methods.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Demonstrates improved robustness and generalization in decision-making.

Effectively mitigates cognitive biases in multi-agent collaboration.

Abstract

Multi-agent systems (MAS) powered by large language models (LLMs) hold significant promise for solving complex decision-making tasks. However, the core process of collaborative decision-making (CDM) within these systems remains underexplored. Existing approaches often rely on either ``dictatorial" strategies that are vulnerable to the cognitive biases of a single agent, or ``voting-based" methods that fail to fully harness collective intelligence. To address these limitations, we propose \textbf{AgentCDM}, a structured framework for enhancing collaborative decision-making in LLM-based multi-agent systems. Drawing inspiration from the Analysis of Competing Hypotheses (ACH) in cognitive science, AgentCDM introduces a structured reasoning paradigm that systematically mitigates cognitive biases and shifts decision-making from passive answer selection to active hypothesis evaluation and construction. To internalize this reasoning process, we develop a two-stage training paradigm: the first stage uses explicit ACH-inspired scaffolding to guide the model through structured reasoning, while the second stage progressively removes this scaffolding to encourage autonomous generalization. Experiments on multiple benchmark datasets demonstrate that AgentCDM achieves state-of-the-art performance and exhibits strong generalization, validating its effectiveness in improving the quality and robustness of collaborative decisions in MAS.