Understanding Dynamic Diffusion Process of LLM-based Agents under Information Asymmetry

• URL: http://arxiv.org/abs/2502.13160v1
• Date: Sun, 16 Feb 2025 03:02:48 GMT
• Title: Understanding Dynamic Diffusion Process of LLM-based Agents under Information Asymmetry
• Authors: Yiwen Zhang, Yifu Wu, Wenyue Hua, Xuming Hu,
• Abstract summary: We study the dynamics of information diffusion in 12 asymmetric open environments defined by information content and distribution mechanisms. We design a dynamic attention mechanism to help agents allocate attention to different information. We observe the emergence of information cocoons, the evolution of information gaps, and the accumulation of social capital.
• Score: 25.531407745300946
• License:
• Abstract: Large language models have been used to simulate human society using multi-agent systems. Most current social simulation research emphasizes interactive behaviors in fixed environments, ignoring information opacity, relationship variability and diffusion diversity. In this paper, we study the dynamics of information diffusion in 12 asymmetric open environments defined by information content and distribution mechanisms. We first present a general framework to capture the features of information diffusion. Then, we designed a dynamic attention mechanism to help agents allocate attention to different information, addressing the limitations of LLM-based attention. Agents start by responding to external information stimuli within a five-agent group, increasing group size and forming information circles while developing relationships and sharing information. Additionally, we observe the emergence of information cocoons, the evolution of information gaps, and the accumulation of social capital, which are closely linked to psychological, sociological, and communication theories.

Related papers

• Emergence of human-like polarization among large language model agents [61.622596148368906]
  We simulate a networked system involving thousands of large language model agents, discovering their social interactions, result in human-like polarization. Similarities between humans and LLM agents raise concerns about their capacity to amplify societal polarization, but also hold the potential to serve as a valuable testbed for identifying plausible strategies to mitigate it.
  arXiv  Detail & Related papers  (2025-01-09T11:45:05Z)
• Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communities [0.0]
  We study the emergence of agency from scratch by using Large Language Model (LLM)-based agents. By analyzing this multi-agent simulation, we report valuable new insights into how social norms, cooperation, and personality traits can emerge spontaneously.
  arXiv  Detail & Related papers  (2024-11-05T16:49:33Z)
• PersLLM: A Personified Training Approach for Large Language Models [66.16513246245401]
  We propose PersLLM, integrating psychology-grounded principles of personality: social practice, consistency, and dynamic development. We incorporate personality traits directly into the model parameters, enhancing the model's resistance to induction, promoting consistency, and supporting the dynamic evolution of personality.
  arXiv  Detail & Related papers  (2024-07-17T08:13:22Z)
• MONAL: Model Autophagy Analysis for Modeling Human-AI Interactions [11.972017738888825]
  We propose Model Autophagy Analysis (MONAL) for large models' self-consumption explanation. MONAL employs two distinct autophagous loops to elucidate the suppression of human-generated information in the exchange between human and AI systems. We evaluate the capacities of generated models as both creators and disseminators of information.
  arXiv  Detail & Related papers  (2024-02-17T13:02:54Z)
• Agent AI: Surveying the Horizons of Multimodal Interaction [83.18367129924997]
  "Agent AI" is a class of interactive systems that can perceive visual stimuli, language inputs, and other environmentally-grounded data. We envision a future where people can easily create any virtual reality or simulated scene and interact with agents embodied within the virtual environment.
  arXiv  Detail & Related papers  (2024-01-07T19:11:18Z)
• MIDDAG: Where Does Our News Go? Investigating Information Diffusion via Community-Level Information Pathways [114.42360191723469]
  We present MIDDAG, an intuitive, interactive system that visualizes the information propagation paths on social media triggered by COVID-19-related news articles. We construct communities among users and develop the propagation forecasting capability, enabling tracing and understanding of how information is disseminated at a higher level.
  arXiv  Detail & Related papers  (2023-10-04T02:08:11Z)
• Decentralized Adversarial Training over Graphs [55.28669771020857]
  The vulnerability of machine learning models to adversarial attacks has been attracting considerable attention in recent years. This work studies adversarial training over graphs, where individual agents are subjected to varied strength perturbation space.
  arXiv  Detail & Related papers  (2023-03-23T15:05:16Z)
• Information is Power: Intrinsic Control via Information Capture [110.3143711650806]
  We argue that a compact and general learning objective is to minimize the entropy of the agent's state visitation estimated using a latent state-space model. This objective induces an agent to both gather information about its environment, corresponding to reducing uncertainty, and to gain control over its environment, corresponding to reducing the unpredictability of future world states.
  arXiv  Detail & Related papers  (2021-12-07T18:50:42Z)
• Learning Representation over Dynamic Graph using Aggregation-Diffusion Mechanism [4.729833950299859]
  We propose an aggregation-diffusion (AD) mechanism that actively propagates information to its neighbor by diffusion after the node updates its embedding through the aggregation mechanism. In experiments on two real-world datasets in the dynamic link prediction task, the AD mechanism outperforms the baseline models that only use aggregation to propagate information.
  arXiv  Detail & Related papers  (2021-06-03T08:25:42Z)
• An active inference model of collective intelligence [0.0]
  This paper posits a minimal agent-based model that simulates the relationship between local individual-level interaction and collective intelligence. Results show that stepwise cognitive transitions increase system performance by providing complementary mechanisms for alignment between agents' local and global optima.
  arXiv  Detail & Related papers  (2021-04-02T14:32:01Z)
• Information scrambling in a collision model [2.7075104175188116]
  We propose a collision model to simulate the information dynamics in an all-optical system. We find that the information is scrambled if the memory and environmental particles are alternatively squeezed along two directions.
  arXiv  Detail & Related papers  (2020-02-12T09:56:07Z)

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.