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 paper introduces Steiner’s taxonomy of group tasks to study how multi‑agent large language model (LLM) teams scale on disjunctive versus compensatory tasks. By modeling agents as conditionally independent given the item, it shows that plurality voting converges to the modal answer while averaging converges to the item‑level bias. Experiments with 13 open‑weight models and up to 30 agents reveal that disjunctive tasks benefit from larger teams, whereas compensatory tasks like Fermi estimation see little improvement, highlighting that task structure and aggregation method fundamentally determine team scaling.
By Carolina Fortuna, Blaz Bertalanic
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:2608. 15980v1 Announce Type: cross Abstract: Preference benchmarks are built by hiring annotators, and the identity of those annotators is treated as an implementation detail.
By Anik Jha
arXiv:2607. 18310v1 Announce Type: cross Abstract: Synthetic-population tools increasingly run every individual as an independent large language model (LLM) agent.
By Gurkan Ozkan
The study investigates how limited reading capacity and claim wording influence consensus outcomes in language‑model networks. By modeling message capacity as the number of messages an agent reads, the authors show that when agents read fewer than about 6.4 messages on average, a wrong consensus becomes unreachable. However, the wording of a claim—its inherent threshold—can override this effect, leading to incorrect consensus even when most agents start correct.
By Makoto Fukushima