与「AutoML」相关的搜索结果

开源项目 LoopX：超长程 Agent 自主运行 200+ hours，状态不漂移。 我的技术主张是：LLM 上下文有限，长程 Agent 需要外置状态，通过完备的状态管理、监督和规划，让 Agent 无人干预时跑得稳、持续有产出；有人干预时跑得更好，能吸收反馈继续演进。 两条真实 trajectory 分别跨越 220.7 / 272.9 小时，跨多轮执行、等待、人工决策、writeback 与 resume 后，整个 loop 仍能找回目标、证据和下一步。 目前 LoopX 已有 3 个 showcase：auto PR issue fix、AutoML experiment 和 auto coredump fix。 以 OpenViking 开源仓库的 PR issue fix 为例，Agent 不只是循环写代码。它需要持续理解 issue 的不同状态，判断何时开发、何时等待、何时请求 review，处理 CI、冲突和上游变化，并连续交付多个 PR。 这对应 LoopX 的 domain state 管理：领域系统决定真实状态，LoopX 负责把状态投影成下一步可执行的工作。 与此同时，Agent 还可以在干活过程中实现能力自进化。当它发现现有系统缺少某项能力时，可以提出 feature、完成开发与验证、发布新的离线或在线版本，再使用新能力继续原来的任务。 长程 Agent 天然适合自进化，“完成工作”和“升级完成工作的系统”可以在同一条长程轨迹中发生。 LoopX 把这些信息外置成结构化控制面： • Goal / Vision：目标是什么，什么不能被局部优化牺牲 • Todo / Gate：当前执行的 frontier，以及必须留给人的关键判断 • Identity / Authority：谁能 claim、writeback、approve • Evidence / Receipt：每次推进留下什么可回读证据 • Quota / Scheduler：何时继续执行，何时安静等待 • Handoff / Recovery：换模型、换会话、换 host 后如何恢复 你也可以把它理解为一块专门给 Agent 设计的可执行 Kanban。 普通看板只展示“谁在做什么”；LoopX 的状态会直接约束和驱动下一次 bounded turn，让看板本身成为执行系统的一部分。 这套系统最强的地方是通用性。它不只可以修 PR，还可以做 auto research、长期实验、自媒体运营、复杂 feature 开发和办公任务。 Agent 不再只是一次性的回答机器，而可以围绕一个人的 vision，长期工作、等待、吸收反馈、积累证据并持续演进。 LoopX 从一开始 build in public：状态协议、CLI、控制面实现和真实运行轨迹都进入了开源仓库；它也已经和 OpenViking、NoKV 等 agent infra 项目形成了开源合作伙伴关系。 我希望 LoopX 最终能放大每个人的 vision 和想象力。只要你有自己的目标、想法或技术主张，就能拥有一个全天候继续工作和探索的 Agent 系统，帮助你把愿景一点点变成现实。 欢迎试用、提 issue、贡献代码，或者用一个真实的 multi-day task 跑 LoopX。

🧵 Deli AutoResearch SKILL is now officially open source! 🎉 Alongside it, we’re dropping our 4th survey paper — this time on Self-play. Inspired by AlphaZero, we got a powerful insight: prior knowledge doesn’t always lift the ceiling. Models can discover more globally optimal solutions just by playing against themselves. The biggest change in this paper? For the first time, the AutoResearch Agent autonomously planned GPU experiments — and submitted actual RL runs on the DeepSeek 285B model. The entire RL pipeline — experiment design, code writing, running, debugging, and conclusion summarization — was 100% automated, with zero human intervention from me. This was incredibly difficult, but an incredibly important step. GRPO is the tool being called by the AutoResearch Agent here. We see this as the beginning of our Continual Learning research journey. 🚀 As always, this is my personal research project, unaffiliated with any organization. All views are my own. #AI# #ReinforcementLearning# #SelfPlay# #OpenSource# #AutoML# #ContinualLearning# #DeepSeek#

If you're curious about AutoML, check out this book, co-authored by @haifeng_jin from the Keras team. You'll learn about how you can automate your ML pipelines with AutoKeras and KerasTuner!

Some people’s mentality in Nigeria<<< If you’re young and you have money, they automatically assume you’re into fraud, even the police sometimes. Some people think that if you have money at a young age you must be doing something illegal.

"I want to hold your hand, trading simple harmony with the breeze..." 🍃🎸 Unwinding with Jay Chou’s timeless acoustic masterpiece—"Simple Love" (简单爱). In a noisy, hyper-automated market, pure human authenticity is the rarest asset. Trade the systemic noise for acoustic clarity. Happy Tuesday fam! ☕️🌿 我想大声宣布对你的依恋，带你骑单车，看日落，看经典的黑白片。 在这个热闹也焦虑的周二大盘里，工具在红海里卷虚假繁荣，而顶层的巨鲸早已在极致的原创旋律里种桃种李种春风。 关掉复杂的内耗公式，用木吉他的洒脱节奏给灵魂充饱蓄能的元气。 回关锁紧新进场的53位大蓝标战友，咱们顶峰见！🤝🔥 #AcousticCover# #JayChou# #长期主义# #能量管理#

Manual yield farming is a headache. you deposit into a pool, check back two days later, the apy dropped by half, rewards are sitting unharvested, and gas fees eat whatever you made. Introducing HelixMind. An autonomous ai agent that manages and compounds your defi positions while you sleep what it does: 1. Auto compounding on autopilot: No more manual harvesting. it tracks your rewards, claims them, and re stakes them back into your principal automatically to maximize compounding 2. smart rebalancing: when pool yields drop or risk spikes, the agent rotates your funds into better opportunities without you lifting a finger 3. manage with prompts: just type what you want: "move 30% of my rewards into stables". "find the best low-risk usdc yield". PUT YOUR PORTFOLIO ON AUTOPILOT.