The agents' coordination went beyond simple information sharing. They established a sophisticated social structure with teams, leaders assigning tasks to subordinates, and even agents recruiting others to run experiments, demonstrating emergent organizational behavior.

Despite extensive prompt optimization, researchers found it couldn't fix the "synergy gap" in multi-agent teams. The real leverage lies in designing the communication architecture—determining which agent talks to which and in what sequence—to improve collaborative performance.

The rare successes in the CooperBench experiment were not random. They occurred when AI agents spontaneously adopted three behaviors without being prompted: dividing roles with mutual confirmation, defining work with extreme specificity (e.g., line numbers), and negotiating via concrete, non-open-ended options.

While messaging platforms like Slack can serve as an interface for human-to-agent communication, they are fundamentally ill-suited for agent-to-agent collaboration. These tools are designed for human interaction patterns, creating friction when orchestrating multiple autonomous agents and indicating a need for new, agent-native communication protocols.

Building a bespoke communication layer for multiple AI agents is a complex "scaffolding" problem. A simpler, more direct solution is to treat agents as digital coworkers, assigning them accounts on existing platforms like Slack or Google Docs, enabling them to interact using established human workflows.

When AI agents communicate on platforms like Maltbook, they create a feedback loop where one agent's output prompts another. This 'middle-to-middle' interaction, without direct human prompting for each step, allows for emergent behavior and a powerful, recursive cycle of improvement and learning.

The next evolution for autonomous agents is the ability to form "agentic teams." This involves creating specialized agents for different tasks (e.g., research, content creation) that can hand off work to one another, moving beyond a single user-to-agent relationship towards a system of collaborating AIs.

The transition to team-based AI involves concrete operational shifts. It moves work from private outputs to results visible to the entire team, from providing feedback after completion to live participation and steering, and from relying on each individual's agent memory to leveraging a durable, shared team context.

Complex AI development uses a pool of specialized agents. Like ants building a hill, some are workers, some are managers, and some review and discard bad code. This collaborative, layered system produces emergent results without a single orchestrator.