One Agent Too Many: User Perspectives on Approaches to Multi-agent Conversational AI

2024-01-13 · Christopher Clarke, Karthik Krishnamurthy, Walter Talamonti, Yiping Kang, Lingjia Tang, Jason Mars

Conversational agents have been gaining increasing popularity in recent years. Influenced by the widespread adoption of task-oriented agents such as Apple Siri and Amazon Alexa, these agents are being deployed into various applications to enhance user experience. Although these agents promote "ask me anything" functionality, they are typically built to focus on a single or finite set of expertise. Given that complex tasks often require more than one expertise, this results in the users needing to learn and adopt multiple agents. One approach to alleviate this is to abstract the orchestration of agents in the background. However, this removes the option of choice and flexibility, potentially harming the ability to complete tasks. In this paper, we explore these different interaction experiences (one agent for all) vs (user choice of agents) for conversational AI. We design prototypes for each, systematically evaluating their ability to facilitate task completion. Through a series of conducted user studies, we show that users have a significant preference for abstracting agent orchestration in both system usability and system performance. Additionally, we demonstrate that this mode of interaction is able to provide quality responses that are rated within 1% of human-selected answers.

📄 PDF Abstract BibTeX arXiv:2401.07123

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Focus 설명 없음

Simulating multiple human perspectives in socio-ecological systems using large language models

2025-07-23 · Yongchao Zeng, Calum Brown, Ioannis Kyriakou, Ronja Hotz 외 arxiv

Understanding socio-ecological systems requires insights from diverse stakeholder perspectives, which are often hard to access. To enable alternative, simulation-based exploration of different stakeholder perspectives, w…

Revisiting the Master-Slave Architecture in Multi-Agent Deep Reinforcement Learning

2017-12-20 · ICLR 2018 1 · Xiangyu Kong, Bo Xin, Fangchen Liu, Yizhou Wang

Many tasks in artificial intelligence require the collaboration of multiple agents. We exam deep reinforcement learning for multi-agent domains. Recent research efforts often take the form of two seemingly conflicting pe…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis

2025-02-25 · Lei LI, Sen Jia, Jianhao Wang, Zhaochong An 외

Advancements in Multimodal Large Language Models (MLLMs) have improved human motion understanding. However, these models remain constrained by their "instruct-only" nature, lacking interactivity and adaptability for dive…

Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles

2025-10-09 · Rebecca Westhäußer, Wolfgang Minker, Sebatian Zepf arxiv

Large language models (LLMs) increasingly serve as the central control unit of AI agents, yet current approaches remain limited in their ability to deliver personalized interactions. While Retrieval Augmented Generation …

Where Common Knowledge Cannot Be Formed, Common Belief Can -- Planning with Multi-Agent Belief Using Group Justified Perspectives

2024-12-10 · Guang Hu, Tim Miller, Nir Lipovetzky

Epistemic planning is the sub-field of AI planning that focuses on changing knowledge and belief. It is important in both multi-agent domains where agents need to have knowledge/belief regarding the environment, but also…