Knowledge Boundary and Persona Dynamic Shape A Better Social Media Agent
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.
Code (1)
Tasks
World KnowledgeSimilar Papers 제목 키워드 기반
BPDO:Boundary Points Dynamic Optimization for Arbitrary Shape Scene Text Detection
Arbitrary shape scene text detection is of great importance in scene understanding tasks. Due to the complexity and diversity of text in natural scenes, existing scene text algorithms have limited accuracy for detecting …
DiversityScene Text DetectionScene UnderstandingText DetectionActive Learning over DNN: Automated Engineering Design Optimization for Fluid Dynamics Based on Self-Simulated Dataset
Optimizing fluid-dynamic performance is an important engineering task. Traditionally, experts design shapes based on empirical estimations and verify them through expensive experiments. This costly process, both in terms…
Active LearningMemory as Asset: From Agent-centric to Human-centric Memory Management
We proudly introduce Memory-as-Asset, a new memory paradigm towards human-centric artificial general intelligence (AGI). In this paper, we formally emphasize that human-centric, personal memory management is a prerequisi…
Persona-based Multi-Agent Collaboration for Brainstorming
We demonstrate the importance of persona-based multi-agents brainstorming for both diverse topics and subject matter ideation. Prior work has shown that generalized multi-agent collaboration often provides better reasoni…
Fine-grained Recurrent Neural Networks for Automatic Prostate Segmentation in Ultrasound Images
Boundary incompleteness raises great challenges to automatic prostate segmentation in ultrasound images. Shape prior can provide strong guidance in estimating the missing boundary, but traditional shape models often suff…
Image SegmentationMedical Image SegmentationSemantic Segmentation