ARIS: Agentic and Relationship Intelligence System for Social Robots

TL;DR

ARIS is a modular social robot framework that combines multimodal reasoning, social relationship modeling, and retrieval-augmented generation to improve multi-turn engagement and social reasoning, validated on Pepper robot.

Contribution

It introduces a social world model with a knowledge graph, an efficient RAG-based dialogue pipeline, and an integrated agentic architecture for social robots, with empirical validation.

Findings

ARIS outperforms a large language model baseline in perceived social intelligence.

User study shows higher ratings of animacy and likeability with ARIS.

ARIS maintains low latency in long dialogues while preserving relevance.

Abstract

Foundational models have advanced social robotics, enabling richer perception and communicative interaction with users. However, current systems still struggle with multi-turn engagement, social-relationship reasoning, and contextually grounded dialogue at scale. We present ARIS (Agentic and Relationship Intelligence System), an agentic AI framework that unifies multimodal reasoning, a graph-based Social World Model, and retrieval-augmented generation (RAG) within a single modular architecture for social robots. We evaluate ARIS with the Pepper robot in a robot-mediated dyadic conversational setting, comparing it against a large language model baseline. A user study (N=23) shows that ARIS yields significantly higher perceived intelligence, animacy, anthropomorphism, and likeability. Our contributions are threefold: (1)~a Social World Model that explicitly maps and updates social relationships between users through a knowledge graph, enabling social reasoning and re-identification across encounters; (2)~an efficient RAG-based conversational pipeline that maintains bounded latency as dialogue histories grow to thousands of exchanges while preserving response relevance; and (3)~system integration and empirical validation of these components within a modular agentic architecture that coordinates speech, vision, and physical action through structured APIs. The implementation of ARIS will be released as open source upon publication.