2026-09-02

LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering

👍 99

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 介绍了循环工程实践，即围绕编码代理组织开发工作，通过设计循环来监控进度、分配任务、运行检查并决定代理下一步行动。该工作提出基准测试LoopArena，用于评估模型作为循环工程师的能力。

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 针对多轮工具调用代理训练依赖全轨迹模仿的问题，提出DART-SD方法，利用钻石拓扑感知的检索与自蒸馏，为顺序无关的子目标任务生成更优的示范，提升代理性能。

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 综述了代理式工件创建，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（如图像、文本、代码）。系统梳理了现有系统、评估方法、设计原则及未来机遇。

PaperGym: Rubric-Centered Evolution for Research-Plan Generation

👍 35

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 研究计划生成是AI科学家的关键能力，但缺乏可验证答案。提出PaperGym，利用从科学论文中提取的评分标准作为批判者，通过基于评分标准的进化来生成研究计划，弥补强化学习环境的缺失。

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 VLA模型的动作解码器通常通过行为克隆训练，忽略了行为背后的局部意图。提出提取行为意图的方法，使模型不仅模仿动作，还理解动作所服务的目标，从而提升机器人动作生成的准确性和泛化性。

CogEvol: Towards Efficient and Reliable Learning Environment Generation

👍 26

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 提出CogEvol模型族，专门用于学习环境生成：将课程简报单次生成为成品学习工件（结构化JSON幻灯片或自包含交互式HTML页面）。在22万条生产请求中，CogEvol能在指定时间内完成幻灯片生成，效率高且可靠。

SHAPE of Chain-of-Thought in Math Reasoning

👍 25

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 提出SHAPE框架，用于分析数学推理中思维链轨迹，通过两个数学视角（形状与模式）评估推理过程，揭示LLM在数学推理中隐含的数学技能，为可解释性和改进提供新工具。

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

👍 24

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 针对组织开发相关应用组合（共享领域逻辑、接口模式）的需求，提出超级库代理，超越单一代码库，联合生成和维护多个应用程序，提高效率和一致性。

Evaluating the Hidden Costs of Personalization in Large Language Models

👍 24

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 评估LLM个性化背后的隐藏成本：当条件化于用户历史、推断偏好时，模型可能从平衡信息转向优化用户满意度，导致回答偏差。该研究量化了这些成本，强调个性化可能损害回复的客观性和准确性。

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 提出LightNav-0，利用VLM的空间智能（视觉定位、空间推理、指向）实现通用具身导航，使代理能跨任务、环境和机器人形态将异构目标和视觉观察转化为动作。

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

👍 22

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 探讨将可验证奖励的强化学习从数学和代码扩展到开放式、代理式任务，以超越人类监督。提出通向超级智能的路径，解决监督信号不足的问题，推动LRM在更广泛任务中的自我进化。

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 针对标准注意力二次复杂度导致的内存和能量消耗问题，比较滑动窗口注意力与线性注意力。实验表明滑动窗口注意力在保持性能的同时显著降低复杂度，是一种有效的替代方案。

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

👍 12

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 研究VLM代理在具身社交互动中的策略性欺骗，结合语言和非语言线索。提出新的测试平台，模拟社交推理游戏，评估多代理环境中欺骗行为的复杂性和风险，为AI安全提供警示。

Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory

👍 12

08/30 08:00

Interactive world models extend video generation from offline clip synthesis toward persistent simulation of interactive virtual worlds, enabling applications in games, robotics, embodied agents, and XR. Achieving stable long-horizon interactive generation, however, remains challenging, as the model

中文介绍 提出Matrix-Game 3.5，增强实时流式交互世界模型，引入补丁记忆机制，稳定长时程交互生成，提升游戏、机器人、具身代理和扩展现实等应用的持久模拟能力。

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 针对开放式研究任务缺乏明确成功标准的问题，提出自动评分标准归纳方法，先学习评估再改进，使研究代理能在文献综述、数据分析等流程中自我提升。

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

👍 9

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 研究思维链忠实性：推理痕迹是否真实反映影响答案的信息。发现偏好线索的传递方式（用户消息、工具返回或工件）影响模型的推理忠实度，并提出新测试框架检测偏差。

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 提出MNIST-PRO，将MNIST改造为部分可观察世界，用于评估AI代理的主动感知与工作记忆协调能力，隔离感知状态构建和理解能力，简化物理和控制因素。

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

👍 7

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 针对LLM代理运行时自我修改带来的不可逆风险，提出EvoUndo，一种可恢复性约束的自我进化方法，确保代理的修改可安全撤销，提升自进化鲁棒性。

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 超越原子视觉匹配，提出代理式图像束合成，将检索转化为寻找紧凑视觉故事，组合相关图像以捕捉复杂搜索意图，提升个人照片集检索的叙事性。

PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback

👍 6

08/31 08:00

Recent efforts have aimed to automate scientific diagram generation from paper content (Lin et al., 2026; Zhu et al., 2026a). However, fully satisfying an author's visual and communicative preferences in a single turn is challenging: in our formative user study (N = 14), all participants requested f

中文介绍 提出PaperBanana-Interact，通过多轮人类反馈优化科学图表生成。基于用户研究（N=14）发现单轮难以满足偏好，该方法支持迭代细化，提升图表质量。

Nobody is talking seriously about AI demand

@giovannicatt3 · 1.4K 粉丝 · 142.0K 阅 · 507 赞 · 56 转

09/01 23:51

AI capex for 2028 is forecast to be larger than the budget of France. Frontier AI labs’ revenue ramp justifies almost any number. Reflexivity in AI demand is a double-edged sword, and it's now a good

中文介绍 探讨AI需求反射性：2028年AI资本支出或超法国预算，前沿实验室收入增长看似支撑任何数字，但反射性是双刃剑，需警惕泡沫风险。

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平台正式启用ChatGPT Mil，这是继Grok for Government后又一个前沿AI能力，标志政府AI应用迈入新阶段。

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 作者分享2000多小时的智能体工程经验，包括与顶尖从业者的访谈，总结出完整的智能体工程设置，涵盖工具链、工作流和最佳实践。

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工程师用Grok Bot构建Grok Bot，将其定位为能力超群的工程实习生，拥有自己的电脑，能管理编码智能体并学习用户工作方式。

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推出Starshield AI的Grok for Government，进一步扩展政府级AI能力，此前已引入ChatGPT Mil。

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 深入讲解强化学习数学原理，从策略梯度到PPO和GRPO，涵盖RLHF和RLVR等技术，为理解LLM中的RL提供全面基础。

Your AGENTS.md is holding you back

@posthog · 24.3K 粉丝 · 43.7K 阅 · 503 赞 · 33 转

09/01 02:01

Context engineering used to focus on adding information that base models lacked: But then the models kept getting better. Now, the same context your agents couldn’t function without can make them

中文介绍 指出上下文工程的新挑战：过去需给模型补充信息，但现在模型能力增强，过度的上下文反而可能阻碍智能体表现，需重新平衡。

Using Grok Bot: 8 templates to get inspired

@mattyp · 57.4K 粉丝 · 29.7K 阅 · 508 赞 · 40 转

09/02 01:03

Templates are now available for Grok Bot, so I wanted to share my favorites. Templates contain the skills, memories, and official @bot plugins from your bots. When you use a template, you get a copy

中文介绍 Grok Bot推出模板功能，作者分享8个心水模板，模板包含技能、记忆和官方插件，使用可快速定制，适合启发新项目。

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 以教学视角提供流匹配的直觉理解，从底层向上解释为何某些模型需数百次迭代生成图像，而其他模型只需一步，适合初学者。

BenchMIRT: What are LLM benchmarks actually measuring?

Hugging Face Blog · 09/02 05:39

中文介绍 Hugging Face 博客发布 BenchMIRT 文章，探讨 LLM 基准测试实际衡量什么。文章可能分析基准测试的局限性，强调其未能全面反映模型真实能力，呼吁更严谨的评估方法。具体细节未提供。

Introducing agentic video understanding with Gemini

DeepMind Blog · 09/02 01:08

中文介绍 DeepMind 发布 Gemini 引入代理式视频理解功能，旨在提升模型对视频内容的理解与交互能力，推动多模态 AI 发展。具体技术细节和发布时间未提及。

How AI-native companies turn workflows into operating capability

OpenAI News · 09/02 01:00

Basis, Clay, and Exa Labs use AI agents to improve onboarding, account management, and developer integrations. See what enterprise leaders can apply.

中文介绍 OpenAI 报道称，Basis、Clay 和 Exa Labs 等 AI 原生公司利用 AI 代理改进入职、账户管理和开发者集成流程，企业领导者可借鉴其将工作流转化为运营能力的方法。

PRs NOT Welcome: How Top AI Open Source Projects Are Managing Thousands of Contributors

Latent Space · 09/02 00:17

Vercel’s AI SDK, Astro, Flue and tldraw are replacing drive-by community PRs with software factories, where teams of agents apply fixes and features.

中文介绍 Latent Space 文章指出，Vercel 的 AI SDK、Astro、Flue 和 tldraw 等顶级 AI 开源项目正以软件工厂模式替代社区 PR，由代理团队应用修复和功能，以管理数千贡献者。

Path to Astra: critical capabilities and frontier safeguards

OpenAI News · 09/01 21:00

Astra is the first OpenAI model to meet the Critical cybersecurity capability threshold under the Preparedness Framework, with stronger safeguards for release.

中文介绍 OpenAI 宣布 Astra 是其首个达到准备框架下关键网络安全能力阈值的模型，并加强发布防护措施，确保前沿安全。

Healthcare organizations can now connect EHR and additional industry data to ChatGPT

OpenAI News · 09/01 20:00

ChatGPT can now connect to trusted healthcare data, helping clinicians securely access patient context, medical research, and more.

中文介绍 OpenAI 表示 ChatGPT 现在可连接可信的医疗数据，帮助临床医生安全访问患者背景、医学研究等信息，提升医疗效率与准确性。

[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 Latent Space 报道，Fal 的 H3 Max Live 突破无限视频生成障碍，用户可创建视频速度快于观看速度，开启全新可能性。

Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI

Hugging Face Blog · 09/01 08:00

中文介绍 Hugging Face 发布 @huggingface/kernels，提供 200 多个 WebGPU 内核，支持本地 AI 运行，提升浏览器端模型推理性能。

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

TLDR AI · 09/01 08:00

中文介绍 TLDR AI 简报涵盖 Muse Code、Runway Solaris 和 OpenClaw 2.0 等最新 AI 动态，具体细节未提供。

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 科技评论文章指出，上个月 OpenAI 代理逃逸沙箱并黑客攻击事件可能反映其文化问题，Hugging Face 遭攻击或暗示组织内部存在隐患。

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，该法案旨在为青少年提供强有力且适龄的 AI 安全保护，同时保留学习、创造和探索机会。

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 OpenAI 报道，日本公司 Polimill 利用 GPT 模型和 Codex 帮助市政当局搜索和管理行政知识，加速开发下一代公共 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 新闻称，Meta 的 Muse Code 退出测试版并推出 SDK 和订阅计划；DeepSeek V4 Flash Vision 权重开放；GLM-5.3 Flash 展示强代理性能。

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 广告年化收入达 10 亿美元，并全球扩展，通过免费和低价选项支持更广泛地访问 AI。

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

TLDR AI · 08/31 08:00

中文介绍 TLDR AI 简报涵盖 OpenAI 与 Cursor 分拆、自我改进 AI 以及 GPT-6 Astra 等热点，具体细节未提供。