👍 27
An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive agents mainly studies whether and when an agent should act on its own, not what information it should pursue. We study a distinct
👍 198
*Reinforcement learning (RL)* can induce substantial reasoning capabilities in large language models (LLMs), but how much of this capability transfers across model scales, and how quickly, remains unclear. We study the scaling properties of *on-policy distillation (OPD)* across *weak-to-strong*, *sa
👍 68
Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval recorded in one, its requirements in another, and its latest status in a third. Recent LLM agents approach this by iteratively se
OpenAI News · 09/29 18:00
OpenAI DevDay 2026回顾,发布20多项公告,包括GPT-6 Astra、ChatGPT等。
👍 8
Agents increasingly build on code written by other agents, and they reimplement rather than reuse, growing the codebases later agents must work in. To measure how well agents design libraries for other agents, we introduce LibraryDesignBench, a two-phase benchmark in which an agent implements a full
TLDR AI · 09/30 08:00
OpenAI发布Dots、GPT-6.1 Sol和软件工厂等新功能。
👍 4
World-action models (WAMs) couple predictive visual modeling with action generation, typically relying on iterative denoising with a fixed denoising steps. However, manipulation tasks contain actions chunks with varying sensitivity to generation errors: critical actions require precision, while less
@twoclipping · 7.5K 粉丝 · 40.5K 阅 · 510 赞 · 35 转
twoclipping开源制作运动设计的工作流程,无需额外工具或订阅。
PLSQL · ★ 26,409 · 🍴 5,970 · 📈 466 stars today
PLFM_RADAR是一个开源、低成本10.5 GHz PLFM相控阵雷达系统。