Agent Context Protocols Enhance Collective Inference
This addresses the challenge of building generalist AI systems by improving interoperability and fault tolerance in multi-agent collaboration, representing a novel method rather than an incremental improvement.
The paper tackles the problem of coordination in multi-agent systems by introducing Agent Context Protocols (ACPs), which use structured communication to enhance collective inference, resulting in state-of-the-art performance such as 28.3% accuracy on AssistantBench for long-horizon web assistance and best-in-class multimodal technical reports.
AI agents have become increasingly adept at complex tasks such as coding, reasoning, and multimodal understanding. However, building generalist systems requires moving beyond individual agents to collective inference -- a paradigm where multi-agent systems with diverse, task-specialized agents complement one another through structured communication and collaboration. Today, coordination is usually handled with imprecise, ad-hoc natural language, which limits complex interaction and hinders interoperability with domain-specific agents. We introduce Agent context protocols (ACPs): a domain- and agent-agnostic family of structured protocols for agent-agent communication, coordination, and error handling. ACPs combine (i) persistent execution blueprints -- explicit dependency graphs that store intermediate agent outputs -- with (ii) standardized message schemas, enabling robust and fault-tolerant multi-agent collective inference. ACP-powered generalist systems reach state-of-the-art performance: 28.3 % accuracy on AssistantBench for long-horizon web assistance and best-in-class multimodal technical reports, outperforming commercial AI systems in human evaluation. ACPs are highly modular and extensible, allowing practitioners to build top-tier generalist agents quickly.