The study examines how shared item‑level error limits the benefit of aggregating small language models in Fermi estimation tasks. By decomposing log10 errors into item‑specific and residual components across 2.51 million answers from 15 open‑weight models, it finds that item‑level error accounts for about 91% of variance, reducing the expected error gain from 74–79% to only 1.7–5.4% when using teams of thirty. Additional techniques such as debate, model mixing, and temperature adjustments offer modest improvements, but no method surpasses the most accurate single model.
By Carolina Fortuna, Blaz Bertalanic
The study examines how shared item‑level error limits the benefit of aggregating small language models in Fermi estimation tasks. By decomposing log10 errors into item‑specific and residual components across 2.51 M answers from 15 open‑weight models, it finds that item‑level error accounts for about 91 % of variance, reducing the expected error gain from a 30‑model team to only 1.7 % (max 5.4 %) instead of the theoretical 74‑79 %. Techniques such as three rounds of debate, model mixing, and temperature adjustments yield modest improvements, but no method surpasses the most accurate single model.
arXiv:2609.35928v1 Announce Type: cross
Abstract: Multi-agent LLM systems increasingly mix models from several providers, yet exposing each agent's underlying model identity to its peers significantl...
By Xavier Del Giudice, Alessio Palma, Matteo Migliarini, Fabio Galasso, Indro Spinelli
arXiv:2608.22152v1 Announce Type: new
Abstract: Multi-agent systems built from large language models are deployed widely, yet how much performance is lost when two LLMs must coordinate rather than ac...
By Weixiang Sun, Zehong Wang, Hong Huang, Colby Nelson, Yanfang Ye
The study evaluates multi‑agent debate (MAD) in small language models, testing whether cognitive diversity—via personas, sampling temperature, or model identity—drives performance gains. Across 23 models, five tasks, and over 5,500 runs, MAD consistently outperforms single‑model inference but, when matched for generation budget, it ties or falls behind self‑consistency sampling, with persona prompting actually reducing accuracy. The authors find that MAD’s benefits largely stem from the first answer exchange and that many reported gains are due to ensemble‑sampling effects rather than true diversity, highlighting the need for budget‑matched, contamination‑checked baselines.
whyItMatters":"The findings clarify that MAD’s perceived advantages may be overestimated and that future debate mechanisms must be evaluated against rigorous, budget‑matched baselines to ensure genuine performance improvements."
By Leonardo Ferreira, Gardenia Liu, Kaden Zheng
arXiv:2606. 02646v1 Announce Type: cross Abstract: Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence.
By Bla\v{z} Bertalani\v{c}, Carolina Fortuna
Agent evaluations increasingly benchmark LLMs, but rankings can be swayed by evaluation conditions such as scaffolds or tasks, making reliability claim‑dependent. A Bayesian variance‑decomposition framework applied to 22 benchmarks shows that reliability varies with the measurement goal: fixed model‑scaffold systems rank reliably, while underlying‑model rankings are less stable. Scaffold choice can alter conclusions, and adding more tasks only modestly improves reliability when scaffold coverage is limited; however, pooling diverse benchmarks can substantially raise cross‑task ranking reliability and reduce cost.
By Michael Hardy, Ruhana Azam, Anka Reuel, Mykel Kochenderfer, Sanmi Koyejo
arXiv:2606. 31174v1 Announce Type: new Abstract: Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized subagents, delegates work, and orchestrates their parallel, asynchronous returns through dynamic workflows.
By Kaiwen Xiong, Haonian Ji, Shi Qiu, Zeyu Zheng, Cihang Xie, Xinyu Ye, Huaxiu Yao
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:2606. 00655v1 Announce Type: cross Abstract: The burgeoning field of LLM-based Multi-Agent Systems (MAS) promises to tackle complex tasks through collaborative intelligence, yet fundamental questions regarding their scaling behavior and intrinsic collective dynamics remain underexplored.
By Jialing Li, Zhouhong Gu, Yin Cai, Hongwei Feng
The paper investigates how scaling a team of small language‑model agents affects performance across different orchestration architectures. By testing eight architectures on five short‑answer benchmarks and an executable‑code benchmark, it finds that team scaling yields large gains on arithmetic word‑problem tasks but only modest improvements on multiple‑choice and code generation tasks, with no single architecture dominating all tasks. The authors explain these patterns using a generate‑transform decomposition that separates coverage and transformation effects, showing that arithmetic tasks benefit from both coverage and critic‑guided transformation, while other tasks are limited by saturation or poor conversion.
By Blaz Bertalanic, Carolina Fortuna
arXiv:2605. 11404v2 Announce Type: replace Abstract: Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents.
By Ling Tang, Jilin Mei, Qian Chen, Qihan Ren, Linfeng Zhang, Quanshi Zhang, Jing Shao, Xia Hu, Dongrui Liu