While multi-agent and model collaboration algorithms gain traction to combine the strengths of diverse Large Language Models (LLMs), existing systems remain bottlenecked on pre-defined and hand-crafte...
arXiv:2609.38816v1 Announce Type: new
Abstract: While multi-agent and model collaboration algorithms gain traction to combine the strengths of diverse Large Language Models (LLMs), existing systems r...
By Zongwan Cao, Ziyuan Yang, Shangbin Feng, Michael Duan, Skyler Hallinan, Bingbing Wen, Lucy Lu Wang, Yulia Tsvetkov
arXiv:2603. 20324v2 Announce Type: replace-cross Abstract: Multi-agent LLM pipelines produce contradictory evidence on whether team diversity improves output quality: heterogeneous Mixture-of-Agents teams outperform single models, yet homogeneous Self-MoA teams consistently win under synthesis-based aggregation.
By Artem Maryanskyy, Dmitry Budnikov, Alibek T. Kaliyev
arXiv:2607. 27177v1 Announce Type: new Abstract: Effective collaboration with novel and diverse partners is a crucial skill for autonomous agents.
By Peter Tisnikar, Maja Swieczkowska, Benteng Ma, Gerard Canal, Matteo Leonetti
arXiv:2607. 29087v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in enterprise settings, yet individual models remain bounded by model-specific capability limitations.
By Yanbin Fang, Xuan Wei, Wei Chen
arXiv:2504. 03991v2 Announce Type: replace-cross Abstract: Understanding how humans collaborate and communicate in teams is essential for improving human-agent teaming and AI-assisted decision-making.
By Siddharth Srikanth, Varun Bhatt, Boshen Zhang, Werner Hager, Charles Michael Lewis, Katia P. Sycara, Aaquib Tabrez, Stefanos Nikolaidis
arXiv:2610.15513v1 Announce Type: cross
Abstract: Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teamin...
By Abrar Alotaibi, Moataz Ahmed
arXiv:2510. 25340v2 Announce Type: replace-cross Abstract: Learning to collaborate with various unfamiliar teammates poses a great challenge in the domain of multi-agent systems.
By Beiwen Zhang, Yongheng Liang, Guowei Zou, Haitao Wang, Liu Cong, Hejun Wu
arXiv:2607. 02198v1 Announce Type: cross Abstract: Human-AI teaming has received increasing attention in the literature.
By Nathan Hughes, Ibrahim Habli
TandemBench is a new benchmark comprising 1,200 multi‑agent cooking scenarios designed to test decision models’ ability to select optimal team plans and judge the optimality of provided options. The dataset gives models full global information and candidate plans, with reference answers derived from execution and exact search. Evaluation of 40 native decision models and 10 general‑purpose language models shows that while the best native model reaches 62.50% accuracy, many models still struggle to correctly assess whether the supplied options contain an optimal arrangement.
By Baohang Li, Xiaocheng Feng, Bing Qin
arXiv:2604.20658v2 Announce Type: replace
Abstract: Multi-agent systems built from teams of large language models (LLMs) are increasingly deployed for collaborative scientific reasoning and problem-s...
By Shivani Kumar, Adarsh Bharathwaj, David Jurgens
arXiv:2610.17456v1 Announce Type: cross
Abstract: Language models are often evaluated alone but increasingly deployed together, routed between, made to debate, ensembled, or collaboratively trained....
By Shangbin Feng, Yulia Tsvetkov, Jan Kautz, David Acuna