(2025-07-14) Willison Anthropic How We Built Our Multiagent Research System

Simon Sillison on Anthropic: How we built our multi-agent research system. OK, I'm sold on multi-agent LLM systems now. I've been pretty skeptical of these until recently

This new article describes a more sophisticated approach.

They start strong by providing a clear definition of how they'll be using the term "AI agent" - it's the "tools in a loop" variant:

Why use multiple agents for a research system? The essence of search is compression: distilling insights from a vast corpus. Subagents facilitate compression by operating in parallel with their own context windows, exploring different aspects of the question simultaneously before condensing the most important tokens for the lead research agent

As anyone who has spent time with Claude Code will already have noticed, the downside of this architecture is that it can burn a lot more tokens:
In our data, agents typically use about 4× more tokens than chat interactions, and multi-agent systems use about 15× more tokens than chats.

Providing a "memory" mechanism is important as well: The LeadResearcher begins by thinking through the approach and saving its plan to Memory to persist the context, since if the context window exceeds 200,000 tokens it will be truncated and it is important to retain the plan.

an interesting description of the OODA research loop used by the sub-agents: Research loop: Execute an excellent OODA (observe, orient, decide, act) loop by (a) observing what information has been gathered so far, what still needs to be gathered to accomplish the task, and what tools are available currently; (b) orienting toward what tools and queries would be best to gather the needed information and updating beliefs based on what has been learned so far; (c) making an informed, well-reasoned decision to use a specific tool in a certain way; (d) acting to use this tool. Repeat this loop in an efficient way to research well and learn based on new results.