SGTO-MAS: Secure Gorilla Troops Optimization for Multi-Agent LLM Systems

2026-06-05

AI Summary

This work addresses the challenges of error propagation, security risks, and computational inefficiency in multi-agent large language model (LLM) coordination, where existing approaches struggle to balance performance, safety, and resource costs. The study introduces, for the first time, a safety-aware adaptive agent selection mechanism, formulating collaboration as a constrained optimization problem. It integrates trust modeling, risk-aware evaluation, and a group intelligence strategy inspired by Gorilla Troop Optimization (GTO) into a unified safety-aware objective. Experimental results demonstrate that the proposed system achieves an average performance of 0.5281, consensus level of 0.8764, and risk below 0.3 across 500 independent runs, using only 4.04 agents on average with a per-run latency of 24.09 seconds. Moreover, performance degradation under perturbations remains within 5.3%, highlighting its effectiveness in jointly optimizing performance, safety, and efficiency.

Abstract

Multi-agent large language model (LLM) systems offer strong capabilities for complex reasoning and decision-making, yet coordination across agents introduces error propagation, security risks, and inefficient use of resources. Existing methods often rely on heuristic, static strategies and lack a principled mechanism for balancing performance, security, and computational cost. This paper formulates multi-agent LLM coordination as a constrained optimization problem and proposes a security-aware method for adaptive agent selection. The method integrates trust modeling, risk-aware evaluation, and collective intelligence within a unified optimization objective. To solve the problem efficiently, we use a swarm-intelligence strategy inspired by Gorilla Troops Optimization (GTO), enabling adaptive coordination under varying threat conditions. Controlled experiments across 500 independent runs demonstrate the effectiveness of the proposed method. The system achieves a stable average performance score of 0.5281, with high consensus (0.8764), controlled risk (0.3000), and compact agent subsets averaging 4.04 selected agents. The optimization process converges efficiently, with an average runtime of 24.09 seconds per run and low score variability (standard deviation = 0.0173). Robustness analysis indicates graceful degradation under perturbations, with performance drops limited to 2.5% under agent removal and 5.3% under consensus disruption. These results show that effective multi-agent coordination can be achieved through structured optimization that jointly manages performance, security, and efficiency. The proposed method provides a practical security-aware solution for coordinating multi-agent LLM systems in complex adversarial settings.

Problem

• multi-agent LLM systems
• error propagation
• security risks
• resource efficiency
• agent coordination

Innovation

• Secure Multi-Agent LLM
• Constrained Optimization
• Gorilla Troops Optimization
• Trust Modeling
• Risk-Aware Coordination