arXiv:2608. 03501v1 Announce Type: new Abstract: AI for Research (AI4Research) leverages AI to automate and improve scientific workflows.
By Zejun Liu, Jian Wu, Ru Peng, Yuliang Ji, Dongyuan Li, Renhe Jiang, Yue Zhang
arXiv:2604.18616v2 Announce Type: replace-cross
Abstract: LLM coding agents can generate correct GPU kernels, but their performance still trails expert libraries. Reaching peak throughput requires co...
By Haohui Mai, Xiaoyan Guo, Xiangyun Ding, Daifeng Li, Qiuchu Yu, Chenzhun Guo, Cong Wang, Jiacheng Zhao, Christos Kozyrakis, Binhang Yuan
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:2607. 14568v1 Announce Type: cross Abstract: A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in device memory (arXiv:2606.
By A. C. Opus, J. Q. Lu
The paper reports on a large‑scale verified search experiment using a 30B language model on a laptop, evaluating three operator packages—schematic notebooks, named obstacles, and behavioural repulsion—in a factorial design across nine construction problems. Results show that the full composition of operators closes the seed‑to‑record gap more effectively than any single component, increases construction‑hash diversity, and that memory plus repulsion consistently avoids collapse. A frontier proposer achieves similar gains in far fewer samples, but the search ultimately stalls near a plateau where the reference family is adopted and optimized only when provided as code.
By Roberto I. Ono Filho
arXiv:2607. 11696v1 Announce Type: new Abstract: Self-refinement often fails to strengthen few-shot inductive reasoning in large language models.
By Huan Zhu