Explicit Trait Inference for Multi-Agent Coordination

2026-04-21

AI Summary

Large language model (LLM)-based multi-agent systems often fail to coordinate effectively in complex tasks due to goal drift, error cascades, and behavioral inconsistency. This work proposes Explicit Trait Inference (ETI), a method enabling agents to reliably infer and track their partners’ traits along two psychological dimensions—warmth (e.g., trustworthiness) and competence (e.g., skill)—from interaction histories, thereby guiding collaborative decision-making. As the first study to systematically demonstrate that LLMs possess the capacity for inferring others’ traits, ETI significantly enhances coordination performance through structured trait-based reasoning: it reduces payoff loss by 45–77% in economic games and improves task performance by 3–29% on MultiAgentBench, with gains strongly correlated with the accuracy of trait inference.

Technology Category

Multiagent Systems: TeamworkHumans and AI: Human-Aware Planning and Behavior PredictionCognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsEconomics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAISearch and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

LLM-based multi-agent systems (MAS) show promise on complex tasks but remain prone to coordination failures such as goal drift, error cascades, and misaligned behaviors. We propose Explicit Trait Inference (ETI), a psychologically grounded method for improving coordination. ETI enables agents to infer and track partner characteristics along two established psychological dimensions--warmth (e.g., trust) and competence (e.g., skill)--from interaction histories to guide decisions. We evaluate ETI in controlled settings (economic games), where it reduces payoff loss by 45-77%, and in more realistic, complex multi-agent settings (MultiAgentBench), where it improves performance by 3-29% depending on the scenario and model, relative to a CoT baseline. Additional analysis shows that gains are closely linked to trait inference: ETI profiles predict agents' actions, and informative profiles drive improvements. These results highlight ETI as a lightweight and robust mechanism for improving coordination in diverse multi-agent settings, and provide the first systematic evidence that LLM agents can (i) reliably infer others' traits from interaction histories and (ii) leverage structured awareness of others' traits for coordination.

Problem

• multi-agent coordination
• coordination failures
• goal drift
• error cascades
• misaligned behaviors

Innovation

• Explicit Trait Inference
• multi-agent coordination
• large language models
• psychological traits
• interaction history