Autonomous Software Agent
Autonomous software agents are computational entities designed to perform complex tasks independently, often mimicking human workflows in diverse domains like software engineering and clinical decision-making. Current research emphasizes improving agent capabilities through advanced search algorithms (like Monte Carlo Tree Search), multi-agent collaboration, and the integration of large language models (LLMs) with multimodal data processing for enhanced reasoning and decision-making in dynamic environments. This field is significant due to its potential to automate intricate processes, improve efficiency in various sectors, and advance our understanding of intelligence and decision-making in complex systems.
Papers
Towards Unified Alignment Between Agents, Humans, and Environment
Zonghan Yang, An Liu, Zijun Liu, Kaiming Liu, Fangzhou Xiong, Yile Wang, Zeyuan Yang, Qingyuan Hu, Xinrui Chen, Zhenhe Zhang, Fuwen Luo, Zhicheng Guo, Peng Li, Yang Liu
Ensuring trustworthy and ethical behaviour in intelligent logical agents
Stefania Costantini