@techreport{mackay-aacp-03,
    number =    {draft-mackay-aacp-03},
    type =      {Internet-Draft},
    institution =   {Internet Engineering Task Force},
    publisher = {Internet Engineering Task Force},
    note =      {Work in Progress},
    url =       {https://datatracker.ietf.org/doc/draft-mackay-aacp/03/},
    author =    {Andrew Mackay},
    title =     {{Agent Action Compression Protocol (AACP) Version 1.4}},
    pagetotal = 16,
    year =      2026,
    month =     jun,
    day =       17,
    abstract =  {This document defines the Agent Action Compression Protocol (AACP), a typed coordination format for agent-to-agent communication in multi- agent large language model (LLM) systems. AACP transforms natural language coordination instructions into deterministic, machine- parseable packets that can be validated before transmission, logged as structured audit records, and replayed consistently across workflow runs. AACP addresses a coordination content layer that existing agent protocols do not cover. The Model Context Protocol (MCP) and Agent- to-Agent Protocol (A2A) operate at the tool access and routing layers respectively. Neither specifies what agents say to each other inside coordination messages. AACP fills this gap with a shared, typed vocabulary for agent coordination intent. For known workflow types, a rule-based encoder produces AACP packets deterministically at zero LLM cost. A four-tier fallback extends this to novel instructions: community registry lookup at zero cost; local cache lookup at zero cost; pattern matching at zero cost; LLM encoding for genuinely novel instructions, logged to registry for permanent reuse. An amortisation benchmark across 240 encoding operations demonstrated 91.6 percent cost saving versus per-call LLM encoding, with 6 LLM calls required across the full run. As a secondary benefit, AACP reduces coordination token usage by approximately 23 percent versus equivalent natural language instructions. Framework integration benchmarks demonstrate 18 percent total workflow cost reduction in LangChain (59 coordination hops) and 30 percent in CrewAI (59 coordination hops), with all coordination LLM calls eliminated in both cases. This document updates draft-mackay-aacp-02 with: framework integration results for AutoGen (55 percent total cost reduction, 59 coordination hops) and Pydantic AI (85 percent total cost reduction, 59 coordination hops); a four-framework comparison demonstrating that AACP saving scales with framework coordination verbosity; a new framing for typed-result frameworks showing that AACP completes the determinism picture by adding typed instructions to complement existing typed results; and publication of five packages on PyPI and npm covering all four frameworks.},
}