Paper - ChatDev: Communicative Agents for Software Development

Coordinates multiple specialized AI agents (CEO, CTO, programmer, tester) through a role-based communication protocol where each agent has distinct responsibilities and communicates via structured message passing. Agents maintain conversation history and context across development phases (requirements analysis, architecture design, implementation, testing), with a central coordinator managing task delegation and phase transitions based on agent outputs.

Implements a structured message-passing system where agents exchange information through a shared conversation history that persists across turns. Each agent reads prior messages, generates responses following role-specific templates, and appends to a growing transcript. The protocol includes semantic routing — agents can reference specific prior messages and the system maintains context windows to prevent token overflow while preserving critical architectural decisions.

Decomposes software development into discrete phases (requirements analysis, architecture design, implementation, testing) where each phase has specific agent responsibilities and success criteria. The system enforces phase ordering — agents cannot proceed to implementation until architecture is approved, and testing only occurs after code generation. Phase transitions are triggered by agent outputs meeting implicit quality thresholds or explicit approval signals.

Assigns distinct roles to agents (CEO for strategic planning, CTO for technical architecture, Programmer for implementation, Tester for validation) and uses role-specific system prompts that constrain each agent's behavior and output format. The CEO agent synthesizes requirements and delegates tasks; the CTO designs architecture and validates feasibility; the Programmer implements based on specifications; the Tester generates test cases and validates correctness. Each role has implicit constraints on what outputs are acceptable.

Translates high-level architecture designs (produced by the CTO agent) into executable source code through a Programmer agent that reads architectural constraints, module definitions, and API specifications. The Programmer generates code that adheres to the specified architecture, including file structure, module boundaries, and inter-module communication patterns. The system supports multiple programming languages and generates complete, runnable projects rather than code snippets.

A Tester agent automatically generates test cases based on code specifications and implementation details, then validates the generated code against those tests. The Tester reads the implementation code, infers test scenarios from function signatures and documented behavior, generates test cases in the appropriate framework (pytest, Jest, etc.), and reports pass/fail results. The system can identify bugs in generated code and flag them for developer review.

A CEO agent reads natural language project requirements and translates them into structured specifications that guide downstream agents. The CEO analyzes requirements for completeness, identifies ambiguities, decomposes high-level goals into concrete tasks, and produces a specification document that includes functional requirements, non-functional constraints, and success criteria. This specification becomes the input for the CTO's architecture design phase.

A CTO agent designs software architecture based on specifications, proposing module structure, component interactions, technology choices, and design patterns. The CTO validates architectural feasibility by checking for circular dependencies, ensuring modules are cohesive, and confirming that the design can be implemented with available technologies. The architecture is documented in a format that the Programmer agent can use to generate code, including module definitions, APIs, and inter-module communication patterns.

Generates executable code in multiple programming languages (Python, JavaScript, Java, C++, etc.) by using language-specific code generation templates and patterns. The system understands language idioms, standard libraries, and framework conventions for each target language, producing idiomatic code rather than direct translations. The Programmer agent selects appropriate language features and design patterns based on the target language's strengths.

Agents can request clarification from users or other agents when specifications are ambiguous or incomplete. The system maintains a conversation interface where agents ask questions, users provide answers, and those answers are incorporated into the specification. This creates an iterative refinement loop where the system progressively clarifies requirements and specifications through dialogue rather than requiring complete specifications upfront.