Repoagent: An llm-powered open-source framework for repository-level code documentation generation

Q Luo, Y Ye, S Liang, Z Zhang, Y Qin, Y Lu… - arXiv preprint arXiv …, 2024 - arxiv.org
Generative models have demonstrated considerable potential in software engineering,
particularly in tasks such as code generation and debugging. However, their utilization in the …

Knowagent: Knowledge-augmented planning for llm-based agents

Y Zhu, S Qiao, Y Ou, S Deng, N Zhang, S Lyu… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Language Models (LLMs) have demonstrated great potential in complex reasoning
tasks, yet they fall short when tackling more sophisticated challenges, especially when …

Towards responsible generative ai: A reference architecture for designing foundation model based agents

Q Lu, L Zhu, X Xu, Z Xing, S Harrer… - 2024 IEEE 21st …, 2024 - ieeexplore.ieee.org
Foundation models, such as large language models (LLMs), have been widely recognised
as transformative AI technologies due to their capabilities to understand and generate …

Screenagent: A vision language model-driven computer control agent

R Niu, J Li, S Wang, Y Fu, X Hu, X Leng, H Kong… - arXiv preprint arXiv …, 2024 - arxiv.org
Existing Large Language Models (LLM) can invoke a variety of tools and APIs to complete
complex tasks. The computer, as the most powerful and universal tool, could potentially be …

Automating the Enterprise with Foundation Models

M Wornow, A Narayan, K Opsahl-Ong… - arXiv preprint arXiv …, 2024 - arxiv.org
Automating enterprise workflows could unlock $4 trillion/year in productivity gains. Despite
being of interest to the data management community for decades, the ultimate vision of end …

ProcessCarbonAgent: A large language models-empowered autonomous agent for decision-making in manufacturing carbon emission management

T Wu, J Li, J Bao, Q Liu - Journal of Manufacturing Systems, 2024 - Elsevier
Abstract Knowledge-intensive production represents a primary trend in industrial
manufacturing, which heavily relies on the production logs of large-scale, historically similar …

FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents

R Xiao, W Ma, K Wang, Y Wu, J Zhao, H Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
LLM-based agents have emerged as promising tools, which are crafted to fulfill complex
tasks by iterative planning and action. However, these agents are susceptible to undesired …

A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Model

J Zhou, Q Lu, J Chen, L Zhu, X Xu, Z Xing… - arXiv preprint arXiv …, 2024 - arxiv.org
The rapid advancement of AI technology has led to widespread applications of agent
systems across various domains. However, the need for detailed architecture design poses …

MAO: A Framework for Process Model Generation with Multi-Agent Orchestration

L Lin, Y Jin, Y Zhou, W Chen, C Qian - arXiv preprint arXiv:2408.01916, 2024 - arxiv.org
Process models are frequently used in software engineering to describe business
requirements, guide software testing and control system improvement. However, traditional …

Benchmarking stereotype bias and toxicity in large language models

R Dutta - 2024 - ideals.illinois.edu
Large language models (LLMs) powered by the transformer architecture have displayed
tremendous advancements in the field of natural language processing (NLP). LLMs pre …