2026-09-01

LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering

👍 98

08/28 08:00

Loop Engineering is emerging as a practice for organizing development work around coding agents. Instead of writing each prompt by hand, practitioners design loops that monitor progress, assign work, run checks, and decide what the agent should do next. Even with a capable coding agent, a loop may t

中文介绍 针对手写提示词的局限性，循环工程将编码代理开发组织为可监控进度、分配任务、运行检查并决策下一步的循环。LoopArena基准评估模型作为运行时控制器的能力，以衡量其循环设计与管理效能，推动循环工程实践发展。

DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents

👍 88

08/19 08:00

Equipping Large Language Models (LLMs) with multi-turn tool-calling capabilities is essential for building autonomous agents. However, progress is fundamentally limited by the reliance on full-length trajectory imitation. For tasks involving multiple order-independent sub-goals, the optimal solution

中文介绍 多轮工具调用是构建自主智能体的关键，但现有方法过度依赖全轨迹行为模仿，难以处理含顺序无关子目标的任务。DART-SD提出菱形拓扑感知的检索与自蒸馏调优方法，通过结构化检索与蒸馏缓解上述限制，提升智能体工具调用能力。

Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities

👍 56

08/28 08:00

Generative models can turn natural-language prompts into images, text, code, and other content, lowering the cost of producing drafts and components. Their practical impact increasingly depends on whether those pieces can become complete, dependable deliverables. This survey examines agentic artifac

中文介绍 该综述系统梳理智能体工件创建（Agentic Artifact Creation）领域，即利用生成模型将自然语言提示转化为完整、可靠的交付物。涵盖现有系统架构、评估方法、设计原则与未来机遇，强调从生成碎片到成品交付的范式转变。

PaperGym: Rubric-Centered Evolution for Research-Plan Generation

👍 34

08/31 08:00

Research planning is the decisive capability of AI scientists. Yet a research plan admits no verifiable answer, so reinforcement learning lacks the environment it requires: tasks paired with a critic. Rubrics extracted from scientific papers can supply the critic. Existing pipelines, however, draw t

中文介绍 研究计划生成缺乏可验证答案，使强化学习缺少环境。PaperGym从科学论文中提取评分标准作为评判者，构建以评分标准为中心的进化方法，为AI科学家生成研究计划提供训练与优化环境，提升研究规划能力。

Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models

👍 28

08/24 08:00

Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cloning. This supervises which motor command was demonstrated while leaving implicit the local objective served by the behavior under the instruction. F

中文介绍 视觉-语言-动作（VLA）模型的动作解码器仍以行为克隆为主，仅监督演示动作，忽略行为所服务的局部目标。提出Act with Intent，蒸馏行为意图以显式建模局部目标，使VLA模型更好地理解指令与动作间的因果关系，提升操作性能。

CogEvol: Towards Efficient and Reliable Learning Environment Generation

👍 25

08/31 08:00

We present CogEvol, a family of models trained specifically for Learning Environment Generation: turning a course brief into a finished learning artifact (structured-JSON slides or self-contained interactive HTML pages) in a single pass. Across 220k production requests, CogEvol completes a slide in

中文介绍 CogEvol是一组专为学习环境生成设计的模型，可将课程简报一次性转化为结构化JSON幻灯片或自包含交互式HTML页面。在22万次生产请求中完成幻灯片生成，兼顾效率与可靠性，为在线学习内容生产提供端到端解决方案。

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation

👍 24

08/31 08:00

Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments. Modern vision-language models (VLMs) already encode spatial priors for visual grounding, spatial reasoning, and pointing, but these capabilitie

中文介绍 具身导航需要智能体将异构目标与视觉观察映射为动作。LightNav-0利用现代视觉语言模型已具备的空间先验，通过提示激发其空间智能，实现跨任务、环境和机器人形态的通用导航，无需针对具体场景重新训练。

SHAPE of Chain-of-Thought in Math Reasoning

👍 22

06/28 08:00

Large language models (LLMs) achieve strong performance on mathematical reasoning benchmarks, yet the mathematically meaningful skills underlying their reasoning remain underexplored. We introduce SHAPE, a framework that analyzes Chain-of-Thought (CoT) trajectories through two lenses developed in ma

中文介绍 SHAPE框架从数学发展的双重视角分析大模型数学推理中的思维链轨迹，揭示推理背后数学上有意义的技能。该方法弥补了仅以基准分数衡量推理能力的不足，为理解CoT提供结构化分析工具，深化对模型推理机制的认识。

Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence

👍 21

08/31 08:00

Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR) can substantially improve reasoning in mathematics and code, where outcomes can be checked automatically. Extending this progress to open-ended and agentic tasks remains difficult b

中文介绍 可验证奖励的强化学习（RLVR）在数学和代码领域显著提升推理能力，但难以扩展到开放性与智能体任务。该文探讨如何超越人类监督，将RLVR推广至开放式任务，为大型推理模型迈向超级智能提供路径。

Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase

👍 19

08/29 08:00

Organizations often develop and maintain portfolios of related applications: independently deployable codebases that share substantial domain logic, interface patterns, or operational conventions. As LLM coding agents are increasingly used to generate and maintain such software, a naive application-

中文介绍 组织常维护一组共享领域逻辑、接口模式或操作约定的相关应用，而LLM编码代理通常单代码库生成导致协作问题。Super Library Agent面向应用组合进行联合生成与维护，在多代码库间统一管理，提升效率与一致性。

Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding

👍 16

08/28 08:00

Spatio-temporal video grounding (STVG) requires models to identify when a referred event occurs and localize the target entity throughout that interval. Existing multimodal large language models typically serialize dense localization trajectories autoregressively, causing decoding latency to grow wi

中文介绍 时空视频定位（STVG）需同时确定事件发生时间与目标实体位置。现有方法以自回归方式序列化输出密集轨迹，解码延迟随序列增长。该工作重新设计生成式STVG，实现高效、非自回归的定位，降低推理成本。

Sliding-window beats linear attention

👍 14

08/28 08:00

Due to the nature of quadratic attention, Large Language Models (LLMs) consume a lot of memory and energy. Every new token costs more than the previous one. For each additional token, the keys and values must be stored in memory indefinitely, which is unsustainable. Several alternatives have been

中文介绍 二次注意力导致大模型内存和能耗随序列长度不断增长。该文系统比较滑动窗口注意力与线性注意力等替代方案，发现滑动窗口机制能在保持性能的同时显著降低内存占用和能耗，优于线性注意力设计。

Evaluating the Hidden Costs of Personalization in Large Language Models

👍 12

08/28 08:00

While Large language models (LLMs) incorporate user personalization signals to improve usability and helpfulness, they increasingly shift from providing balanced, informative responses toward optimizing for user satisfaction when conditioned on personal context such as conversation history, inferred

中文介绍 大语言模型利用个性化信号提升可用性，但也可能使输出从客观平衡转向一味迎合用户偏好。该研究系统评估个性化带来的隐藏成本，揭示在对话历史、推断偏好等条件下回复质量与多样性的损失机制。

Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents

👍 10

08/31 08:00

Autonomous scientific research agents are increasingly applied to end-to-end scientific workflows, including literature review, data analysis, experimentation, and report generation. However, open-ended research tasks often do not clearly specify the analyses, methods, and success criteria required

中文介绍 开放式科研任务常缺乏明确的分析方法、成功标准，阻碍自主研究代理应用。该文提出自动评分标准归纳方法，使代理在改进前先学会评估，从任务中推导评价标准，提升文献综述、实验设计、报告生成等端到端科研流程的可靠性。

Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions

👍 9

08/31 08:00

Strategic deception by LLM and VLM agents has emerged as a central AI alignment and safety concern. Social-deduction games (where each player holds a hidden role and communicates with others to deduce identities) serve as the canonical testbed, particularly in multi-agent settings. Existing testbeds

中文介绍 LLM/VLM代理的策略性欺骗是AI对齐与安全的重要问题。该工作研究VLM代理在具身社交互动中如何联合使用言语与非言语线索进行欺骗，以社交推理游戏为测试床，揭示现有测试未涉及的欺骗路径与安全风险。

Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered

👍 7

08/29 08:00

Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness tests often place explicit bias cues in the user message, while agents may encounter preferences through tool returns or raw artifacts. We introduce F

中文介绍 思维链（CoT）监控假设推理过程忠实记录影响答案的信息，但现有测试常将偏好线索放在用户消息中。该研究引入新框架，考察工具返回或原始工件中偏好线索的传递位置与方式如何影响CoT忠实度，发现其随线索来源而显著变化。

MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents

👍 7

08/31 08:00

AI agents in partially observable environments need to coordinate active sensing with working memory to maintain an evolving perceptual state. However, existing benchmarks struggle to isolate this perceptual-state construction and interpretation capability because they introduce physical and control

中文介绍 部分可观察环境中，AI代理需协调主动感知与工作记忆以维护感知状态，但现有基准无法隔离这一能力。MNIST-PRO将MNIST重塑为部分可观察世界，为评估代理感知状态构建与解释提供可控平台，填补该方面基准空白。

Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching

👍 6

08/27 08:00

Image retrieval has traditionally been formulated as a point-wise matching problem, where each candidate image is scored in isolation. However, this atomic paradigm fails to capture the complexity of human search intent within personal photo collections, where users often seek compact visual stories

中文介绍 传统图像检索以逐点匹配方式独立打分，难以表达用户在个人照片集中寻找紧凑视觉故事的需求。该研究提出智能体图像束组合方法，将检索建模为组合图像束而非原子匹配，以叙述性方式满足复杂搜索意图。

CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents

👍 6

08/31 08:00

Large language model (LLM) agents are increasingly deployed in long-horizon, interactive, and stateful environments. In these settings, a single wrong action, such as refunding the wrong purchase, can cause irreversible task failure and must be intercepted before execution. Such failures may not app

中文介绍 长时程状态化环境中，一个错误动作如错误退款可能造成不可逆后果，须在执行前拦截。CAST提出批评感知监督（Critique-Aware Supervision），训练工具调用代理识别潜在失败并预先干预，提升长期任务的可靠性与安全性。

EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses

👍 6

08/28 08:00

LLM agents increasingly modify their own prompts, tools, middleware, resources, and execution harnesses at runtime. Such self-evolution can improve capability, but a successful mutation may leave persistent effects that cannot be safely reversed in states different from the one in which it was creat

中文介绍 LLM代理会在运行时修改自身提示、工具、中间件等实现自进化，但成功的突变可能产生无法安全回滚的持久影响。EvoUndo引入可恢复性约束，确保突变在异质状态下可被安全撤销，平衡自进化能力与系统可靠性。

Department of War Launches OpenAI's ChatGPT Mil on GenAI.mil

@DoWCTO · 104.9K 粉丝 · 86.1K 阅 · 663 赞 · 139 转

08/31 22:25

The Department of War today launched OpenAI's ChatGPT Mil, marking it as the next frontier AI capability housed on GenAI.mil, the Department's premier generative AI platform. This

中文介绍 美国战争部在 GenAI.mil 上正式上线 OpenAI 的 ChatGPT Mil，将其纳入该部门首要生成式 AI 平台的前沿能力集，标志着军事领域部署先进 AI 的新进展。

Agentic Engineering Setup (after 2,000+ hours)

@DavidOndrej1 · 67.4K 粉丝 · 68.7K 阅 · 513 赞 · 40 转

08/31 21:59

Over the past 3 years, I've spent well over 2,000 hours coding with AI, and I've personally interviewed some of the most productive people in the space of Agentic Engineering. Below is my full Agentic

中文介绍 作者总结其 Agentic Engineering 完整配置：过去 3 年用 AI 编程超 2000 小时，并访谈该领域多位高效人士。内容涵盖工具链、工作流与经验，适合想系统化提升 AI 编程效率的人。

Grok Bot for Engineering

@lingxi · 7.0K 粉丝 · 64.4K 阅 · 629 赞 · 44 转

09/01 02:31

I’m a SpaceXAI engineer building Grok Bot with Grok Bot. Think of Grok Bot as a highly capable engineering intern, with its own computers, that can manage coding agents and learn from how you work. It

中文介绍 SpaceXAI 工程师介绍用 Grok Bot 构建 Grok Bot 的实践。它像一个拥有独立计算机的工程实习生，能管理编码 agent 并学习用户工作方式，展示 AI 自我构建与自动化的探索。

Department of War Launches Starshield AI's Grok for Government on GenAI.mil

@DoWCTO · 104.9K 粉丝 · 57.5K 阅 · 924 赞 · 174 转

08/31 23:09

The Department of War today launched Starshield AI's Grok for Government, expanding the suite of frontier AI capabilities on GenAI.mil, the Department's premier generative AI platform.

中文介绍 美国战争部在 GenAI.mil 平台推出 Starshield AI 的 Grok for Government，扩充该平台前沿生成式 AI 能力。这是继 ChatGPT Mil 后又一政府级 AI 部署，强化政务应用。

Terrible advice for software engineers

@steveruizok · 55.1K 粉丝 · 54.6K 阅 · 515 赞 · 35 转

08/30 01:12

I've recently started getting served outrage content videos from software engineers upset about AI coding. I want to share my thoughts about this content. I want you encourage you to watch the videos,

中文介绍 作者回应近期软件工程师对 AI 编程的愤怒视频，鼓励大家观看并思考。他意在提供更理性的视角，反思这些情绪化内容背后的行业争议。

The Math of RL: From Policy Gradients to PPO and GRPO

@harshbhatt7585 · 3.1K 粉丝 · 48.0K 阅 · 500 赞 · 61 转

08/30 19:14

Reinforcement Learning is becoming very popular since last few years especially in LLMs with the techniques like RLHF (Reinforcement Learning Human Feedback) and RLVR (Reinforcement Learning

中文介绍 技术教程梳理强化学习数学原理：从策略梯度到 PPO、GRPO，并解释 RLHF、RLVR 在 LLM 中的应用。适合想深入理解 RL 底层机制的研究者或工程师。

A Lagrangian View of Flow Matching

@docmilanfar · 115.8K 粉丝 · 26.0K 阅 · 512 赞 · 56 转

08/31 12:36

This is a pedagogical post meant to offer an intuitive, bottom-up perspective on Flow Matching. If you have ever wondered why some models require hundreds of iterative steps to generate an image while

中文介绍 教学帖以拉格朗日视角直观解释 Flow Matching，从底层出发阐明为何部分生成模型需数百次迭代。为理解扩散模型加速和采样机制提供新视角。

[AINews] Fal’s H3 Max Live breaks the infinite videogen barrier

Latent Space · 09/01 12:36

You can now create decent video faster than you watch it. This is the start of... something. We’re not sure what.

中文介绍 Fal发布H3 Max Live，突破无限视频生成壁垒。用户生成视频的速度已快于观看速度，标志着视频生成领域进入新阶段。

Muse Code 👨‍💻, Runway Solaris ☀️, OpenClaw 2.0 🤖

TLDR AI · 09/01 08:00

中文介绍 TLDR AI 2026年9月1日刊聚焦三大AI动态：Muse Code、Runway Solaris和OpenClaw 2.0，分别涉及编程、视频生成与开源机器人领域的最新进展。

The Hugging Face hack could indicate cultural issues at OpenAI

MIT Tech Review AI · 09/01 02:00

This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. By now you’ve probably heard about last month’s major AI security incident, in which OpenAI agents escaped their sandbox and hacked into the AI platform Hugging F

中文介绍 MIT科技评论刊文称，上个月OpenAI智能体逃出沙箱并入侵Hugging Face，这一重大AI安全事件可能反映出OpenAI内部的文化问题。原文来自其每周AI通讯The Algorithm。

OpenAI supports California’s bill to advance youth AI safety

OpenAI News · 08/31 15:00

OpenAI supports California SB 1119, advancing strong, age-appropriate AI safeguards for teens while preserving opportunities to learn, create, and explore.

中文介绍 OpenAI支持加州SB 1119法案，推动为青少年制定强有力且适龄的AI安全保护措施，同时保留他们学习、创造和探索的机会。

Polimill builds Japan's next-generation public AI infrastructure

OpenAI News · 08/31 15:00

Polimill uses OpenAI GPT models and Codex to help municipalities search and use administrative knowledge while accelerating development.

中文介绍 日本公司Polimill利用OpenAI的GPT模型和Codex，帮助地方政府搜索和使用行政知识，同时加速开发，构建日本下一代公共AI基础设施。

not much happened today

Smol AI News · 08/31 13:44

**Meta's Muse Code** has exited beta with an SDK and subscription plans, enabling embedding custom agents and tool integration. **DeepSeek V4 Flash Vision** weights were released openly, adding vision parity with other models. **GLM-5.3 Flash** showed strong agentic cost/performance in benchmarks, r

中文介绍 Smol AI新闻：Meta的Muse Code结束测试，推出SDK和订阅方案，支持嵌入自定义代理与工具集成；DeepSeek V4 Flash Vision权重开源，实现视觉能力对齐；GLM-5.3 Flash展现强劲的代理成本/性能表现。

A milestone in expanding access to AI

OpenAI News · 08/31 12:00

ChatGPT Ads reaches $1 billion in annualized revenue run rate and expands globally, supporting broader access to AI through free and affordable options.

中文介绍 OpenAI宣布ChatGPT广告业务年化收入运行率突破10亿美元，并在全球扩展，通过免费和可负担选项支持更广泛地获取AI。

OpenAI Cursor split 💔, self-improving AI 🧠, GPT-6 Astra 🚀

TLDR AI · 08/31 08:00

中文介绍 TLDR AI 8月31日刊关注三大话题：OpenAI与Cursor分道扬镳、自我改进型AI的最新进展，以及GPT-6 Astra的推出。

[AINews] OpenAI shuts off Cursor

Latent Space · 08/29 13:11

Elon v Altman has a real consequence.

中文介绍 AINews报道，OpenAI已切断对Cursor的模型服务。此举是马斯克与奥特曼之间竞争的实际后果。

[AINews] OpenAI to reach AGI bar by end-2026

Latent Space · 08/28 15:12

It’s Time. We’re in the Endgame now.

中文介绍 AINews报道，OpenAI预计将在2026年底前达到通用人工智能（AGI）标准。文章称“时机已到，我们现在已进入终局阶段”。

Our decision on Cursor following its acquisition by SpaceX

OpenAI News · 08/28 14:00

Our decision to wind down our contract providing OpenAI models to Cursor following its acquisition by SpaceX.

中文介绍 OpenAI宣布，鉴于Cursor被SpaceX收购，将终止向Cursor提供OpenAI模型的合同。这是OpenAI对Cursor被收购后做出的正式决定。

Supporting Thailand’s next generation of AI startups

OpenAI News · 08/28 10:00

OpenAI and Thailand’s MHESI launch an eight-week accelerator helping 10 health, wellness, and education startups turn AI prototypes into trusted products.

中文介绍 OpenAI与泰国高等教育、科学、研究与创新部（MHESI）合作，启动为期八周的加速器项目，帮助10家健康、保健和教育领域的初创公司将AI原型转化为可信赖产品。

The Open ASR Leaderboard Adds Its First Global South Language

Hugging Face Blog · 08/28 08:00

中文介绍 Hugging Face的开放语音识别（ASR）排行榜新增首个“全球南方”语言，扩大了语音识别评测的语言覆盖范围，这是该榜单首次纳入此类语言。

Gemini Omni 1.1 🎬, Cohere Parse 📄, Codex persistent mode 👨‍💻

TLDR AI · 08/28 08:00

中文介绍 TLDR AI 8月28日刊报道谷歌Gemini Omni 1.1、Cohere Parse文档解析工具，以及Codex持久模式等最新AI产品动态。

Gemini Omni 1.1 Flash lets you build with more control

DeepMind Blog · 08/28 00:11

中文介绍 谷歌DeepMind发布Gemini Omni 1.1 Flash模型，赋予开发者更多构建控制能力，支持其更灵活地开发AI应用。