BEHAVE: A Hybrid AI Framework for Real-Time Modeling of Collective Human Dynamics

Helene Malyutina

arXiv:2605.12730 · 2026-05-14 공개 · arXiv · PDF

phase-transitions neural-models behavioral-fields interaction-graph kinematic-signals criticality-index real-time-modeling group-dynamics

Abstract

Existing AI systems for modeling human behavior operate at the level of individuals or detect events after they occur. As a result, they systematically fail to capture the collective dynamics that determine whether a group remains stable or transitions into escalation or breakdown. We propose a different foundation: a group of interacting humans constitutes a complex dynamical system in the precise mathematical sense, exhibiting emergence, nonlinearity, feedback loops, sensitivity near critical points, and phase transitions between qualitatively distinct regimes. The state of such a system is not located within any single participant; it is distributed across mutual influence loops and observable through the micro-dynamics of the body. We introduce BEHAVE (Behavioral Engine for Human Activity Vector Estimation), a formal framework that models collective dynamics as continuous behavioral fields defined over an interaction space derived from observable physical signals. Kinematic micro-signals (position, velocity, body orientation, gestural activity) are structured into a directed interaction graph and aggregated into a basis of behavioral fields capturing distinct, non-redundant axes of collective state. The framework rests on one theorem and two structural propositions characterizing the tension field, the field basis, and the criticality index. Perception and forecasting layers are implemented using neural models, enabling data-driven learning and approximation of system dynamics. BEHAVE is formulated as a computational system for learning, representing, and forecasting collective dynamics from data. A working pipeline is demonstrated on a 7-agent negotiation snapshot. The same fields, recalibrated, apply to crowd safety, crisis-team dynamics, education, and clinical contexts.

한국어 요약

📋 한 줄 요약

**[Computational Social Science / 동역학계]** 인간 집단의 집단 동역학을 관측 가능한 신체 신호 기반 행동 필드로 모델링·예측하는 BEHAVE 프레임워크 제안.

🎯 핵심 기여도

💡 핵심 아이디어

집단의 상태는 단일 참여자 안이 아니라 mutual influence 루프와 신체 micro-dynamics에 분산되어 있다. 이를 행동 필드라는 연속 표현으로 보면 집단의 안정·붕괴·격화를 정량적으로 다룰 수 있다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 집단 행동을 정량·예측 가능한 동역학계로 모델링하는 통합 프레임을 제안해 social-physics 적 접근의 인프라를 제공. **한계**: 7-agent 소규모 데모에 그쳐 대규모 군중·다문화 컨텍스트로의 확장 검증은 후속 과제.

🚀 실용적 활용