Communicative Agents for Software Development
Authors: Chen Qian, Xin Cong, Wei Liu, Cheng Yang, Weize Chen, Yusheng Su, Yufan Dang, Jiahao Li, Juyuan Xu, Dahai Li, Zhiyuan Liu, Maosong Sun
Abstract
Software engineering is a domain characterized by intricate decision-making processes, often relying on nuanced intuition and consultation. Recent advancements in deep learning have started to revolutionize software engineering practices through elaborate designs implemented at various stages of software development. In this paper, we present an innovative paradigm that leverages large language models (LLMs) throughout the entire software development process, streamlining and unifying key processes through natural language communication, thereby eliminating the need for specialized models at each phase. At the core of this paradigm lies ChatDev, a virtual chat-powered software development company that mirrors the established waterfall model, meticulously dividing the development process into four distinct chronological stages: designing, coding, testing, and documenting. Each stage engages a team of agents, such as programmers, code reviewers, and test engineers, fostering collaborative dialogue and facilitating a seamless workflow. The chat chain acts as a facilitator, breaking down each stage into atomic subtasks. This enables dual roles, allowing for proposing and validating solutions through context-aware communication, leading to efficient resolution of specific subtasks. The instrumental analysis of ChatDev highlights its remarkable efficacy in software generation, enabling the completion of the entire software development process in under seven minutes at a cost of less than one dollar. It not only identifies and alleviates potential vulnerabilities but also rectifies potential hallucinations while maintaining commendable efficiency and cost-effectiveness. The potential of ChatDev unveils fresh possibilities for integrating LLMs into the realm of software development.
The papers around it, by date and closeness
Higher is closer to this paper; left is older. Lines join papers close to each other: groups of lines are sub-topics. Select a point to see why it is there. Back to the summary of this paper
Papers around this one
Ranked by how close their title and abstract are to this paper’s. Select some to read them together.
Closest papers
-
HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at ScaleH. Phan, Phong Nguyen, N. Bui · 2024 · arXiv.org · preprint, not peer reviewed · cited 72 times · Not summarized yet
Abstract
Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software agents utilizing LLMs for end-to-end development tasks, these systems are typically designed for specific SE functions. We introduce HyperAgent, an innovative generalist multi-agent system designed to tackle a wide range of SE tasks across different programming languages by mimicking the workflows of human developers. HyperAgent features four specialized agents-Planner, Navigator, Code Editor, and Executor-capable of handling the entire lifecycle of SE tasks, from initial planni…
-
Enhancing Software Development with Context-Aware Conversational Agents: A User Study on Developer Interactions with ChatbotsGlaucia Melo, Paulo S. C. Alencar, Donald D. Cowan · 2025 · arXiv.org · preprint, not peer reviewed · cited 2 times · Not summarized yet
Abstract
Software development is a cognitively intensive process requiring multitasking, adherence to evolving workflows, and continuous learning. With the rise of large language model (LLM)-based tools, such as conversational agents (CAs), there is growing interest in supporting developers through natural language interaction. However, little is known about the specific features developers seek in these systems. We conducted a user study with 29 developers using a prototype text-based chatbot to investigate preferred functionalities. Our findings reveal strong interest in task automation, version control support, and contextual adaptability, especially the need to tailor assistance for both novice a…
-
Specializing Large-Language Models for Collaboration Workflow Generation in Software EngineeringYassine Elmouhi · 2026 · Proceedings of the ACM/IEEE 29th International Conference on Model Driven Engineering Languages and Systems · Not summarized yet
Abstract
Automated problem solving through teams of Large Language Model (LLM)-based agents has recently made remarkable progress, demonstrating the potential of collaborative approaches for software engineering tasks. Existing approaches generally follow one of two paradigms: they either solve tasks directly without generating an explicit collaboration workflow artifact, or they rely on simple lightweight collaboration artifacts. We hypothesize that generating expressive and formal collaboration workflow artifacts with rich control-flow semantics can improve the orchestration of specialized AI agents for complex software engineering tasks. This thesis investigates methods for specializing LLMs to au…
-
LLMs' Reshaping of People, Processes, Products, and Society in Software Development: A Comprehensive Exploration with Early AdoptersBenyamin Tabarsi, Heidi Reichert, Ally Limke et al. · 2025 · Empirical Software Engineering, 32, 21 (2027) · cited 22 times · AI summary available
The interview study examines how professional developers use LLMs across software development stages, while ChatDev automates those stages with communicating agents.
Abstract
Large language models (LLMs) like OpenAI ChatGPT, Google Gemini, and GitHub Copilot are rapidly gaining traction in the software industry, but their full impact on software engineering remains insufficiently explored. Despite their growing adoption, there is a notable lack of formal, qualitative assessments of how LLMs are applied in real-world software development contexts. To fill this gap, we conducted semi-structured interviews with sixteen early-adopter professional developers to explore their use of LLMs throughout various stages of the software development life cycle. Our investigation examines four dimensions: people - how LLMs affect individual developers and teams; process - how LL…
-
Developing LLM-based multi-agent systems in software engineering: a mixed-method experience reportMaria Sâmyla Serafim de Oliveira, M. Ibiyo, Marco Gianrusso et al. · 2026 · Empirical Software Engineering · cited 1 time · Not summarized yet
Abstract
The proliferation of Generative Artificial Intelligence (Gen AI) powered by large language models (LLMs) has transformed the software development process, introducing new paradigms for code generation, debugging, testing, and maintenance. While early applications focused on leveraging single, independent LLMs to assist developers with isolated tasks, recent advances have shifted toward multi-agent systems (MAS) that orchestrate multiple LLM-based agents working collaboratively toward common objectives. Despite their promising potential, using MAS encompasses a set of challenges for developers who have to carefully select the right technology, devise proper coordination rules, and design spec…
-
SWE-Dev: Building Software Engineering Agents with Training and Inference ScalingHaoran Wang, Zhen-Yu Hou, Yao Wei et al. · 2025 · Annual Meeting of the Association for Computational Linguistics · cited 35 times · Not summarized yet
Abstract
Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE). Recent LLM-powered toolkits, such as OpenAI Codex and Cursor, have offered end-to-end automation of the software development process. However, building effective SWE agents remains challenging due to the lack of high-quality training data and effective test cases. To address this issue, we present SWE-Dev, an SWE agent built upon open-source LLMs. First, we develop a robust pipeline to synthesize test cases for patch evaluation. Second, we scale up agent trajectories to construct the training data for building SWE-Dev. E…
-
Software as Content: Dynamic Applications as the Human-Agent Interaction LayerMulong Xie, Yang Xie · 2026 · Human-Computer Interaction · preprint, not peer reviewed · cited 2 times · Not summarized yet
Abstract
Chat-based natural language interfaces have emerged as the dominant paradigm for human-agent interaction, yet they fundamentally constrain engagement with structured information and complex tasks. We identify three inherent limitations: the mismatch between structured data and linear text, the high entropy of unconstrained natural language input, and the lack of persistent, evolving interaction state. We introduce Software as Content (SaC), a paradigm in which dynamically generated agentic applications serve as the primary medium of human-agent interaction. Rather than communicating through sequential text exchange, this medium renders task-specific interfaces that present structured informa…
-
Agentless: Demystifying LLM-based Software Engineering AgentsChunqiu Steven Xia, Yinlin Deng, Soren Dunn et al. · 2024 · Software Engineering · preprint, not peer reviewed · cited 568 times · Not summarized yet
Agentless questions whether complex autonomous agents are necessary for software engineering, contrasting with ChatDev’s collaborative multi-agent workflow.
Abstract
Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. More recently, researchers and industry practitioners have developed various autonomous LLM agents to perform end-to-end software development tasks. These agents are equipped with the ability to use tools, run commands, observe feedback from the environment, and plan for future actions. However, the complexity of these agent-based approaches, together with the limited abilities of current LLMs, raises the following question: Do we really have to employ complex autonomous software agents? To attempt to answ…
Prior work it builds on
-
Agents: An Open-source Framework for Autonomous Language AgentsWangchunshu Zhou, Y. Jiang, Long Li et al. · 2023 · arXiv.org · preprint, not peer reviewed · cited 151 times · Not summarized yet
Abstract
Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with environments, humans, and other agents using natural language interfaces. We consider language agents as a promising direction towards artificial general intelligence and release Agents, an open-source library with the goal of opening up these advances to a wider non-specialist audience. Agents is carefully engineered to support important features including planning, memory, tool usage, multi-agent communication, and fine-grained symbolic control. Agents is user-friendly as it enables non-specialists to build, custo…
-
MetaAgents: Large Language Model Based Agents for Decision-Making on TeamingYuan Li, Li-Chao Sun, Yi-Xuan Zhang · 2023 · Proc. ACM Hum. Comput. Interact. · cited 124 times · Not summarized yet
Abstract
Significant advancements have occurred in the application of Large Language Models (LLMs) for social simulations. Despite this, their abilities to perform teaming in task-oriented social events are underexplored. Such capabilities are crucial if LLMs are to effectively mimic human-like social behaviors and form efficient teams to solve tasks. To bridge this gap, we introduce MetaAgents, a social simulation framework populated with LLM-based agents. MetaAgents facilitates agent engagement in conversations and a series of decision making within social contexts, serving as an appropriate platform for investigating interactions and interpersonal decision-making of agents. In particular, we const…
-
ChatEval: Towards Better LLM-based Evaluators through Multi-Agent DebateChi-Min Chan, Weize Chen, Yusheng Su et al. · 2023 · arXiv.org · preprint, not peer reviewed · cited 1,029 times · Not summarized yet
Abstract
Text evaluation has historically posed significant challenges, often demanding substantial labor and time cost. With the emergence of large language models (LLMs), researchers have explored LLMs' potential as alternatives for human evaluation. While these single-agent-based approaches show promise, experimental results suggest that further advancements are needed to bridge the gap between their current effectiveness and human-level evaluation quality. Recognizing that best practices of human evaluation processes often involve multiple human annotators collaborating in the evaluation, we resort to a multi-agent debate framework, moving beyond single-agent prompting strategies. The multi-agent…
-
Emphasizing human capabilities in software developmentS. T. Acuña, N. Juristo, A. Moreno · 2006 · IEEE Software · cited 166 times · Not summarized yet
-
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in AgentsWeize Chen, Yusheng Su, Jingwei Zuo et al. · 2023 · International Conference on Learning Representations · cited 867 times · AI summary available
Abstract
Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often required to enhance the efficiency and effectiveness of task accomplishment. Hence, inspired by human group dynamics, we propose a multi-agent framework \framework that can collaboratively and dynamically adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that \framework framework can effectively deploy multi-agent groups that outperform a single agent. Furthermore, we delve into the emergence of social behaviors …
Papers that cite it
-
A Systematic Survey of Agentic Skills: Architecture, Lifecycle, and SecuritySanket Badhe, D. Shah, Priyanka Tiwari et al. · 2026 · cited 3 times · Not summarized yet
Abstract
Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on complex, long-horizon tasks. While monolithic prompt engineering and stateless tool-calling paradigms struggle to scale, the field is rapidly converging toward \emph{agentic skills}: modular procedural abstractions that externalize execution knowledge into reusable, executable, and portable artifacts. This paper establishes a unified systems foundation and reference architecture for the agentic skills ecosystem. We formalize skills as externalized procedural knowledge bridging high-level cognitive planning with deterministic execution environme…
-
SAGE: Source-Aligned Governance for Human–Agent Requirements Clarification in Multi-agent Software EngineeringTing-Ting Feng, Mei-Fang Xue, Jian Wang et al. · 2026 · Proceedings of the 2nd International Workshop on Multi-Agent Systems using Generative Artificial INtelligence for Automa · Not summarized yet
Abstract
Multi-agent large language model workflows are increasingly used in software engineering, yet requirements clarification under human–agent collaboration remains weakly governed. Much of the rework reflects requirement-chain desynchronization: negotiated intent, workflow contracts, and signed deliverables evolve on separate tracks without auditable linkage, yielding semantic drift and unclear accountability. Source-Aligned Governance and Evolution governs clarification via three co-evolving sources, a clarification–confirmation–sign-off path, three strategies for cross-source mapping, staged human sign-off, and cross-scenario reuse, and ten operational mechanisms—platform-agnostic rules that …
-
A Multiagent-Driven Robotic AI Chemist Enabling Autonomous Chemical Research On DemandTao Song, Man Luo, Xiaolong Zhang et al. · 2025 · Journal of the American Chemical Society · cited 181 times · Not summarized yet
Abstract
The successful integration of large language models (LLMs) into laboratory workflows has demonstrated robust capabilities in natural language processing, autonomous task execution, and collaborative problem-solving. This offers an exciting opportunity to realize the dream of autonomous chemical research on demand. Here, we report a robotic AI chemist powered by a hierarchical multiagent system, ChemAgents, based on an on-board Llama-3.1-70B LLM, capable of executing complex, multistep experiments with minimal human intervention. It operates through a Task Manager agent that interacts with human researchers and coordinates four role-specific agents─Literature Reader, Experiment Designer, Comp…
-
Apodex 1.1: Scaling Agentic Intelligence for Complex WorkB. An, B. Li, B. Wang et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 5 times · Not summarized yet
Abstract
General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, together with state maintenance, failure recovery, and verifiable delivery. We call this \emph{working capability}: sustained, verifiable progress toward a real-world objective. Apodex 1.1 develops this capability along two complementary dimensions. \emph{Environment Scaling} expands the diversity and verifiability of executable file, search, and code environments, while \emph{Agentic Coordination Scaling} trains agents to decompose long-horizon tasks, delegate parallel work, integrate asynchronous results, and replan.…
-
Engineering Design Collaborative Workflows for Research Software Engineering Through a Multi-Agent FrameworkMing-Jun Shi, Jing-Yuan Deng, Liang Li et al. · 2026 · Design and Artificial Intelligence · Not summarized yet
Go further
How are these papers found?
We compare the title and abstract of this paper with those of every paper summarized on this site, and with the papers Semantic Scholar recommends, those it cites and those citing it (for a much-cited paper, its most recent citations and, from OpenAlex, the most cited ones). Among the prior work and the follow-ups, the papers that use each other in depth, a method it uses and the much-cited follow-ups come a little higher. The levels (very close, close, related) come from the similarity of the texts, not from a judgment of quality; * marks a paper without an abstract, compared by its title. The sentence under a paper is written by an AI from the two abstracts: check it in the papers. A paper marked not relevant by three readers leaves the list.
Updated on 5 November 2026.