LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead

Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning

Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin A Raffel. 2022 · 1965

Earlier work this paper cites.

Privacy amplification by public discussion

Charles H Bennett, Gilles Brassard, and Jean-Marc Robert. 1988 · 1988

Earlier work this paper cites.

Concepts and paradigms of object-oriented programming

Peter Wegner. 1990 · 1990

Earlier work this paper cites.

Issues in requirements elicitation

Michael G Christel and Kyo C Kang. 1992 · 1992

Earlier work this paper cites.

Techniques for requirements elicitation. In [1993] Proceedings of the IEEE International Symposium on Requirements Engineering . IEEE, 152–164

Joseph A Goguen and Charlotte Linde. 1993 · 1993

Earlier work this paper cites.

Modeling adaptive autonomous agents

Pattie Maes. 1993 · 1993

Earlier work this paper cites.

Agent-oriented programming

Yoav Shoham. 1993 · 1993

Earlier work this paper cites.

Automatic code generation from design patterns

Frank J. Budinsky, Marilyn A. Finnie, John M. Vlissides, and Patsy S. Yu. 1996 · 1996

Earlier work this paper cites.

Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. In International workshop on agent theories, architectures, and languages . Springer, 21–35

Stan Franklin and Art Graesser. 1996 · 1996

Earlier work this paper cites.

Secure multi-party computation

Oded Goldreich. 1998 · 1998

Earlier work this paper cites.

Role-based access control

Ravi S Sandhu. 1998 · 1998

Earlier work this paper cites.

Managing software requirements: a unified approach

Dean Leffingwell and Don Widrig. 2000 · 2000

Earlier work this paper cites.

Requirements engineering in the year 00: A research perspective. In Proceedings of the 22nd international conference on Software engineering . 5–19

Axel Van Lamsweerde. 2000 · 2000

Earlier work this paper cites.

Autonomous agents: From self-control to autonomy

Alfred R Mele. 2001 · 2001

Earlier work this paper cites.

Role delegation as multi-agent oriented dynamic composition. In Proceedings of Net Object Days (NOD), AgeS workshop, Erfurt, Germany

Denis Jouvin and Salima Hassas. 2002 · 2002

Earlier work this paper cites.

Revealing information while preserving privacy. In Proceedings of the twenty-second ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems . 202–210

Irit Dinur and Kobbi Nissim. 2003 · 2003

Earlier work this paper cites.

Code generation in action

Jack Herrington. 2003 · 2003

Earlier work this paper cites.

Metrics and models in software quality engineering

Stephen H Kan. 2003 · 2003

Earlier work this paper cites.

An introduction to agile methods

David Cohen, Mikael Lindvall, and Patricia Costa. 2004 · 2004

Earlier work this paper cites.

A unified model of requirements elicitation

Ann M Hickey and Alan M Davis. 2004 · 2004

Earlier work this paper cites.

Agile and iterative development: a manager’s guide

Craig Larman. 2004 · 2004

Earlier work this paper cites.

Software quality engineering: testing, quality assurance, and quantifiable improvement

Jeff Tian. 2005 · 2005

Earlier work this paper cites.

Differential privacy. In International colloquium on automata, languages, and programming . Springer, 1–12

Cynthia Dwork. 2006 · 2006

Earlier work this paper cites.

Selecting studies for systemic review: Inclusion and exclusion criteria

Timothy Meline. 2006 · 2006

Earlier work this paper cites.

What makes a good bug report?. In Proceedings of the 16th ACM SIGSOFT International Symposium on Foundations of software engineering . 308–318

Nicolas Bettenburg, Sascha Just, Adrian Schröter, Cathrin Weiss, Rahul Premraj, and Thomas Zimmermann. 2008 · 2008

Earlier work this paper cites.

Distributed agile development: Using scrum in a large project. In 2008 IEEE International Conference on Global Software Engineering . IEEE, 87–95

Maria Paasivaara, Sandra Durasiewicz, and Casper Lassenius. 2008 · 2008

Earlier work this paper cites.

Multi-agent programming

Rafael H Bordini, Mehdi Dastani, Jürgen Dix, and Amal El Fallah Seghrouchni. 2009 · 2009

Earlier work this paper cites.

The waterfall model in large-scale development. In Product-Focused Software Process Improvement: 10th International Conference, PROFES 2009, Oulu, Finland, June 15-17, 2009. Proceedings 10 . Springer, 386–400

Kai Petersen, Claes Wohlin, and Dejan Baca. 2009 · 2009

Earlier work this paper cites.

An introduction to multiagent systems

Michael Wooldridge. 2009 · 2009

Earlier work this paper cites.

Competency mapping: A gap Analysis

Jaideep Kaur and Vikas Kumar. 2013 · 2013

Earlier work this paper cites.

Big data and due process: Toward a framework to redress predictive privacy harms

Kate Crawford and Jason Schultz. 2014 · 2014

Earlier work this paper cites.

Guidelines for snowballing in systematic literature studies and a replication in software engineering. In Proceedings of the 18th international conference on evaluation and assessment in software engineering . 1–10

Claes Wohlin. 2014 · 2014

Earlier work this paper cites.

Homomorphic encryption

Xun Yi, Russell Paulet, Elisa Bertino, Xun Yi, Russell Paulet, and Elisa Bertino. 2014 · 2014

Earlier work this paper cites.

Attribute-based access control

Vincent C Hu, D Richard Kuhn, David F Ferraiolo, and Jeffrey Voas. 2015 · 2015

Earlier work this paper cites.

Software agent systems

Rainer Unland. 2015 · 2015

Earlier work this paper cites.

Agile software development methods: Review and analysis

Original

Pekka Abrahamsson, Outi Salo, Jussi Ronkainen, and Juhani Warsta. 2017 · 2017

Earlier work this paper cites.

The eu general data protection regulation (gdpr)

Paul Voigt and Axel Von dem Bussche. 2017 · 2017

Earlier work this paper cites.

Autonomous agents modelling other agents: A comprehensive survey and open problems

Stefano V Albrecht and Peter Stone. 2018 · 2018

Earlier work this paper cites.

Towards improving decision making and estimating the value of decisions in value-based software engineering: the VALUE framework

Emilia Mendes, Pilar Rodriguez, Vitor Freitas, Simon Baker, and Mohamed Amine Atoui. 2018 · 2018

Earlier work this paper cites.

The california consumer privacy act: Towards a european-style privacy regime in the united states

Stuart L Pardau. 2018 · 2018

Earlier work this paper cites.

Empirical research in software engineering—a literature survey

Li Zhang, Jia-Hao Tian, Jing Jiang, Yi-Jun Liu, Meng-Yuan Pu, and Tao Yue. 2018 · 2018

Earlier work this paper cites.

Blockchain challenges and opportunities: A survey

Zibin Zheng, Shaoan Xie, Hong-Ning Dai, Xiangping Chen, and Huaimin Wang. 2018 · 2018

Earlier work this paper cites.

Agile software development: Methodologies and trends

Samar Al-Saqqa, Samer Sawalha, and Hiba AbdelNabi. 2020 · 2020

Earlier work this paper cites.

Multi-agent oriented programming: programming multi-agent systems using JaCaMo

Olivier Boissier, Rafael H Bordini, Jomi Hubner, and Alessandro Ricci. 2020 · 2020

Earlier work this paper cites.

A survey of compiler testing

Junjie Chen, Jibesh Patra, Michael Pradel, Yingfei Xiong, Hongyu Zhang, Dan Hao, and Lu Zhang. 2020 · 2020

Earlier work this paper cites.

Proactive risk management: Controlling uncertainty in product development

Preston G Smith and Guy M Merritt. 2020 · 2020

Earlier work this paper cites.

Distributed ledger technology

Ali Sunyaev and Ali Sunyaev. 2020 · 2020

Earlier work this paper cites.

A comparative study of vulnerability reporting by software composition analysis tools. In Proceedings of the 15th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM) . 1–11

Nasif Imtiaz, Seaver Thorn, and Laurie Williams. 2021 · 2021

Earlier work this paper cites.

Advances and open problems in federated learning

Peter Kairouz, H Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al · 2021

Earlier work this paper cites.

Automation of systematic literature reviews: A systematic literature review

Raymon Van Dinter, Bedir Tekinerdogan, and Cagatay Catal. 2021 · 2021

Earlier work this paper cites.

Ptm4tag: sharpening tag recommendation of stack overflow posts with pre-trained models. In Proceedings of the 30th IEEE/ACM International Conference on Program Comprehension . 1–11

Junda He, Bowen Xu, Zhou Yang, DongGyun Han, Chengran Yang, and David Lo. 2022 · 2022

Earlier work this paper cites.

Rethinking the entwinement between artificial intelligence and human learning: What capabilities do learners need for a world with AI?

Lina Markauskaite, Rebecca Marrone, Oleksandra Poquet, Simon Knight, Roberto Martinez-Maldonado, Sarah Howard, Jo Tondeur, Maarten De Laat, Simon Buckingham Shum, Dragan Gašević, et al · 2022

Earlier work this paper cites.

An extensive study on pre-trained models for program understanding and generation. In Proceedings of the 31st ACM SIGSOFT international symposium on software testing and analysis . 39–51

Zhengran Zeng, Hanzhuo Tan, Haotian Zhang, Jing Li, Yuqun Zhang, and Lingming Zhang. 2022 · 2022

Earlier work this paper cites.

Llm-deliberation: Evaluating llms with interactive multi-agent negotiation games

Original

Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, and Mario Fritz. 2023 · 2023

Earlier work this paper cites.

Gpt-4 technical report

Original

Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al · 2023

Earlier work this paper cites.

LLM-Coordination: Developing Coordinating Agents with Large Language Models

Saaket Agashe. 2023 · 2023

Earlier work this paper cites.

Low-code llm: Visual programming over llms

Original

Yuzhe Cai, Shaoguang Mao, Wenshan Wu, Zehua Wang, Yaobo Liang, Tao Ge, Chenfei Wu, Wang You, Ting Song, Yan Xia, et al · 2023

Cited alongside, same era.

Scalable multi-robot collaboration with large language models: Centralized or decentralized systems?

Original

Yongchao Chen, Jacob Arkin, Yang Zhang, Nicholas Roy, and Chuchu Fan. 2023a · 2023

Cited alongside, same era.

Pentestgpt: An llm-empowered automatic penetration testing tool

Original

Gelei Deng, Yi Liu, Víctor Mayoral-Vilches, Peng Liu, Yuekang Li, Yuan Xu, Tianwei Zhang, Yang Liu, Martin Pinzger, and Stefan Rass. 2023 · 2023

Cited alongside, same era.

Self-collaboration Code Generation via ChatGPT

Original

Yihong Dong, Xue Jiang, Zhi Jin, and Ge Li. 2023 · 2023

Cited alongside, same era.

A Unified Debugging Approach via LLM-Based Multi-Agent Synergy

Original

Cheryl Lee, Chunqiu Steven Xia, Jen-tse Huang, Zhouruixin Zhu, Lingming Zhang, and Michael R Lyu. 2024 · 2024

Closest in time.

AutoCoder: Enhancing Code Large Language Model with \ \backslash textsc { \{ AIEV-Instruct } \}

Original

Bin Lei, Yuchen Li, and Qiuwu Chen. 2024a · 2024

Closest in time.

Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API Usage

Original

Bin Lei, Yuchen Li, Yiming Zeng, Tao Ren, Yi Luo, Tianyu Shi, Zitian Gao, Zeyu Hu, Weitai Kang, and Qiuwu Chen. 2024b · 2024

Closest in time.

Exploring the Integration of Large Language Models in Industrial Test Maintenance Processes

Original

Ludvig Lemner, Linnea Wahlgren, Gregory Gay, Nasser Mohammadiha, Jingxiong Liu, and Joakim Wennerberg. 2024 · 2024

Closest in time.