Latest

Every published item, in order · 9845 items
Nov 4
Nov 3
PapersBuildersSelected23:57
Alibaba's SPAR Agent Lifts 1688 Merchant Conversion in 200,000-Merchant A/B Test

The attribution step is the detail most agent memory setups skip: it separates lessons worth saving from noise caused by market conditions. The paper (arXiv:2611.01695) offers a template for anyone building agents that learn from production outcomes rather than offline evals. Teams running sales, support or growth agents can adopt the two-loop design without touching model weights.

elvis@omarsar0Source
PapersBuildersSelected22:12
Google deploys agent swarms to fix TPU compiler bugs

Silent miscompilations are a class of failure most teams only discover after a training run collapses, and this paper shows agents can be steered past flashy crash bugs toward that higher-value target. It is also an honest cost account: human review load, not agent capability, became the bottleneck. Practitioners running large-scale training on TPUs can read the bisection pipeline details on arXiv (2611.00624) and consider similar fuzzing setups for their own compilers.

elvis@omarsar0Source
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
PapersMulti-source15:38
Chinese content非凸分布采样新算法:超越对数凹性的近端采样复杂度分析

理论向的文章:作者改进了近端采样器在非凸密度下的查询复杂度,LSI 条件下得到次多项式查询上界,还证明了 PI 情形的 oracle 下界。做采样理论的朋友可以看看证明思路。

Event
arXiv: OpenAI@Wei Guo et al. (6)Source

Only the latest 2000 items are listed; for older ones see the daily archive