Getting Up to Speed on Multi-Agent Systems, Part 1: The Landscape

I’ve been reading multi-agent systems papers for weeks trying to figure out where the field actually is, and the honest answer is that it moves fast enough that any single paper is a snapshot, not a map. So this is the map I wish I’d had when I started. It’s a short series of posts meant to get someone up to speed on multi-agent LLM systems without having to read thirty papers first. Before I start, a note on the frame I’m going to use. I’m going to talk about two “waves” of multi-agent research, and one outside disruption that happened between them. I want to be upfront that the waves are a reader aid, not a historical claim. Nobody in 2023 was writing “wave 1” papers. The field did not hold a meeting and decide what wave it was in. The waves aren’t like French New Wave cinema or second-wave feminism, where participants knew they were part of a movement and defined their work against prior generations. What I’m doing here is retrospective grouping, the kind you do to keep thirty…