Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

We propose MODEL SWARMS, a collaborative search algorithm to adapt LLMs via swarm intelligence, the collective behavior guiding individual systems. Specifically, MODEL SWARMS starts with a pool of LLM experts and a utility function. Guided by the best-found checkpoints across models, diverse LLM experts collaboratively move in the weight space and optimize a utility function representing model adaptation objectives. Compared to existing model composition approaches, MODEL SWARMS offers tuning-free model adaptation, works in lowdata regimes with as few as 200 examples, and does not require assumptions about specific experts in the swarm or how they should be composed. Extensive experiments demonstrate that MODEL SWARMS could flexibly adapt LLM experts to a single task, multi-task domains, reward models, as well as diverse human interests, improving over 12 model composition baselines by up to 21.0% across tasks and contexts. Further analysis reveals that LLM experts discover previously unseen capabilities in initial checkpoints and that MODEL SWARMS enable the weak-tostrong transition of experts through the collaborative search process. Code and data available at https://github.com/BunsenFeng/model swarm . * This is to avoid all particles collapsing into the global best g like a "black hole" and reduce exploration. † All particles perform velocity and location update in parallel, we omit the time stamp k for brevity.