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

Shangbin Feng, Zifeng Wang, Yike Wang, Sayna Ebrahimi, Hamid Palangi, Lesly Miculicich, Achin Kulshrestha, Nathalie Rauschmayr, Yejin Choi, Yulia Tsvetkov, Chen-Yu Lee, Tomas Pfister
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16904-16930, 2025.

Abstract

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 low-data 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-to-strong transition of experts through the collaborative search process.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-feng25o, title = {Model Swarms: Collaborative Search to Adapt {LLM} Experts via Swarm Intelligence}, author = {Feng, Shangbin and Wang, Zifeng and Wang, Yike and Ebrahimi, Sayna and Palangi, Hamid and Miculicich, Lesly and Kulshrestha, Achin and Rauschmayr, Nathalie and Choi, Yejin and Tsvetkov, Yulia and Lee, Chen-Yu and Pfister, Tomas}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {16904--16930}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/feng25o/feng25o.pdf}, url = {https://proceedings.mlr.press/v267/feng25o.html}, abstract = {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 low-data 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-to-strong transition of experts through the collaborative search process.} }
Endnote
%0 Conference Paper %T Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence %A Shangbin Feng %A Zifeng Wang %A Yike Wang %A Sayna Ebrahimi %A Hamid Palangi %A Lesly Miculicich %A Achin Kulshrestha %A Nathalie Rauschmayr %A Yejin Choi %A Yulia Tsvetkov %A Chen-Yu Lee %A Tomas Pfister %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-feng25o %I PMLR %P 16904--16930 %U https://proceedings.mlr.press/v267/feng25o.html %V 267 %X 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 low-data 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-to-strong transition of experts through the collaborative search process.
APA
Feng, S., Wang, Z., Wang, Y., Ebrahimi, S., Palangi, H., Miculicich, L., Kulshrestha, A., Rauschmayr, N., Choi, Y., Tsvetkov, Y., Lee, C. & Pfister, T.. (2025). Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:16904-16930 Available from https://proceedings.mlr.press/v267/feng25o.html.

Related Material