Knowledge Boundary and Persona Dynamic Shape A Better Social Media Agent

• URL: http://arxiv.org/abs/2403.19275v2
• Date: Tue, 2 Apr 2024 10:59:23 GMT
• Title: Knowledge Boundary and Persona Dynamic Shape A Better Social Media Agent
• Authors: Junkai Zhou, Liang Pang, Ya Jing, Jia Gu, Huawei Shen, Xueqi Cheng,
• Abstract summary: We construct a social media agent based on personalized knowledge and dynamic persona information. For personalized knowledge, we add external knowledge sources and match them with the persona information of agents, thereby giving the agent personalized world knowledge. For dynamic persona information, we use current action information to internally retrieve the persona information of the agent, thereby reducing the interference of diverse persona information on the current action.
• Score: 69.12885360755408
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Constructing personalized and anthropomorphic agents holds significant importance in the simulation of social networks. However, there are still two key problems in existing works: the agent possesses world knowledge that does not belong to its personas, and it cannot eliminate the interference of diverse persona information on current actions, which reduces the personalization and anthropomorphism of the agent. To solve the above problems, we construct the social media agent based on personalized knowledge and dynamic persona information. For personalized knowledge, we add external knowledge sources and match them with the persona information of agents, thereby giving the agent personalized world knowledge. For dynamic persona information, we use current action information to internally retrieve the persona information of the agent, thereby reducing the interference of diverse persona information on the current action. To make the agent suitable for social media, we design five basic modules for it: persona, planning, action, memory and reflection. To provide an interaction and verification environment for the agent, we build a social media simulation sandbox. In the experimental verification, automatic and human evaluations demonstrated the effectiveness of the agent we constructed.

Related papers

• PersonaGym: Evaluating Persona Agents and LLMs [47.75926334294358]
  We introduce PersonaGym, the first dynamic evaluation framework for assessing persona agents, and PersonaScore, the first automated human-aligned metric grounded in decision theory. Our evaluation of 6 open and closed-source LLMs, using a benchmark encompassing 200 personas and 10,000 questions, reveals significant opportunities for advancement in persona agent capabilities.
  arXiv  Detail & Related papers  (2024-07-25T22:24:45Z)
• Autonomous Agents for Collaborative Task under Information Asymmetry [31.376542971135354]
  We propose a new MAS paradigm termed iAgents, which denotes Informative Multi-Agent Systems. In iAgents, the human social network is mirrored in the agent network, where agents proactively exchange human information necessary for task resolution. Experiments show that iAgents can collaborate within a social network of 140 individuals and 588 relationships, autonomously communicate over 30 turns, and retrieve information from nearly 70,000 messages to complete tasks within 3 minutes.
  arXiv  Detail & Related papers  (2024-06-21T07:37:19Z)
• Humanoid Agents: Platform for Simulating Human-like Generative Agents [3.259634592022173]
  We propose a system that guides Generative Agents to behave more like humans by introducing three elements of System 1 processing. Humanoid Agents are able to use these dynamic elements to adapt their daily conversations with other agents. Our system is designed to be analytics to various settings, three of which we demonstrate, as well as to other elements influencing human behavior.
  arXiv  Detail & Related papers  (2023-10-09T05:30:42Z)
• Information Design in Multi-Agent Reinforcement Learning [61.140924904755266]
  Reinforcement learning (RL) is inspired by the way human infants and animals learn from the environment. Research in computational economics distills two ways to influence others directly: by providing tangible goods (mechanism design) and by providing information (information design)
  arXiv  Detail & Related papers  (2023-05-08T07:52:15Z)
• Generative Agents: Interactive Simulacra of Human Behavior [86.1026716646289]
  We introduce generative agents--computational software agents that simulate believable human behavior. We describe an architecture that extends a large language model to store a complete record of the agent's experiences. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims.
  arXiv  Detail & Related papers  (2023-04-07T01:55:19Z)
• Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents [60.27066549589362]
  Social language used by human agents is associated with greater users' responsiveness and task completion. The model uses a sequence-to-sequence deep learning architecture, extended with a social language understanding element. Evaluation in terms of content preservation and social language level using both human judgment and automatic linguistic measures shows that the model can generate responses that enable agents to address users' issues in a more socially appropriate way.
  arXiv  Detail & Related papers  (2020-12-29T08:22:48Z)
• Imitating Interactive Intelligence [24.95842455898523]
  We study how to design artificial agents that can interact naturally with humans using the simplification of a virtual environment. To build agents that can robustly interact with humans, we would ideally train them while they interact with humans. We use ideas from inverse reinforcement learning to reduce the disparities between human-human and agent-agent interactive behaviour.
  arXiv  Detail & Related papers  (2020-12-10T13:55:47Z)
• Learning Latent Representations to Influence Multi-Agent Interaction [65.44092264843538]
  We propose a reinforcement learning-based framework for learning latent representations of an agent's policy. We show that our approach outperforms the alternatives and learns to influence the other agent.
  arXiv  Detail & Related papers  (2020-11-12T19:04:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.