2026-09-01

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

👍 185

08/26 08:00

A common strategy for scaling world models is to train on more crawled video with more compute. We argue that this strategy is inefficient: scaling world models also requires a recursive data engine that offers grounded reward signals. The success of code agents illustrates why this matters. As code

中文介绍 提出以可验证轨迹数据引擎扩展世界模型，从游戏开发中获取带奖励信号的数据，用代码智能体验证思路，提升世界模型扩展效率。

UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

👍 106

08/27 08:00

Multimodal large language models (MLLMs) can interpret a street view, but urban agency depends on whether such local evidence remains useful after the agent starts to move. In this paper, we investigate how far current MLLM agents can turn local urban perception into reliable action in a complicated

中文介绍 探究多模态大模型智能体在真实城市中能否将局部感知转化为可靠行动，评估其在复杂环境下的空间决策能力。

LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering

👍 86

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 提出LoopArena基准，评估模型作为循环工程的运行时控制器，用于组织编码智能体开发工作，监控进度并决策后续行动。

TTPO: Test-Time Policy Optimization

👍 72

08/27 08:00

Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models, yet their reliance on ground-truth labels precludes test-time training (TTT). Replacing ground truth wit

中文介绍 提出测试时策略优化（TTPO），无需真实标签即可在测试时训练，解决现有后训练方法依赖标签限制测试时训练的问题，提升数学推理能力。

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

👍 63

08/27 08:00

Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale image-text data because embodied collection is costly and sparsely covers the physical world. This makes representation quality a central bottleneck: u

中文介绍 针对视觉-语言-动作模型，提出表征中心的持续预训练方法，缓解机器人数据难以扩展的瓶颈，提升表征质量以增强泛化。

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

👍 60

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 提出DART-SD，利用钻石拓扑感知的检索与调优，对多轮工具调用智能体进行自蒸馏，避免全轨迹模仿，处理顺序无关子目标任务。

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

👍 51

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 综述生成式智能体制品创建，涵盖系统、评估、原则与机遇，探讨将自然语言提示生成完整可靠交付物的方法。

Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report

👍 47

08/22 08:00

AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low latency, frequent strategy updates, and accurate yet effective responses. Evolvable Harnesses, whose Skills, Hooks, prompts, and tools can be updated indepe

中文介绍 报告TaoLive数字人智能体技术，采用可进化运行环境，实时更新技能、钩子与提示，低延迟执行营销策略并回答产品问题。

GameWAM: A World Action Model for Video Games

👍 45

08/25 08:00

Modern video games combine first-person perception, rapid visual changes, persistent world state, and heterogeneous native controls. Existing game agents map visual and task context directly to actions but lack explicit world dynamics modeling, whereas interactive game world models predict visual fu

中文介绍 提出GameWAM，面向视频游戏的世界动作模型，融合视觉感知与原生控制，显式建模世界动力学，实现交互式游戏玩法。

Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

👍 43

08/27 08:00

Physical understanding and reasoning depend on forming compact and generalizable representations of the world. While modern vision-language models can recognize and explain diverse physical events, they often lack explicit representations of the underlying mechanisms-such as object states, physical

中文介绍 提出以代码作为世界表示，智能体自动发现可执行的世界模型，用于物理推理，显式建模物体状态和物理机制，提升泛化。

J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data

👍 35

08/27 08:00

Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage of reducing the cost of human supervision. While considerable progress has been made in verifiable domains, self-evolution in unverifiable domains remains substantially less explored.

中文介绍 提出J-Zero，零数据下挑战者-求解器-裁判共同进化，实现不可验证领域的语言模型自我进化，降低人工监督成本。

PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents

👍 30

08/27 08:00

Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends, so they cannot redirect the active run or immediately apply and validate lessons learned from it. We argue that self-imp

中文介绍 提出PILOT循环，让长时程智能体在执行中实时自我改进，即时应用经验教训并调整当前运行，提升长期任务性能。

Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

👍 27

08/27 08:00

Language model pretraining has become almost synonymous with prohibitive cost, placing it out of reach for much of the academic and open-source communities. Although strong open-source efforts already exist, including open-weight models and open-source training recipes, a cost-efficient, hardware-ac

中文介绍 报告Puro-2B，基于Qwen2-1.5B在RTX 5090上低成本预训练的语言模型，提供硬件适配的训练方案，降低预训练成本门槛。

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

👍 24

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 提出行为意图蒸馏方法，为视觉-语言-动作模型提取行为背后的局部目标，改进动作解码器，超越简单行为克隆。

ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

👍 24

08/28 08:00

Long-horizon agentic tasks require large language models (LLMs) to iteratively retrieve, integrate, and maintain dispersed information across multi-turn interactions, but preserving all interaction histories leads to a continuously growing working context. Recent proactive context management methods

中文介绍 提出ContextPilot，通过细粒度强化学习教会智能体主动管理上下文，降低长时程任务中工作上下文持续增长的问题。

WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

👍 24

08/27 08:00

Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill developme

中文介绍 提出WikiSkill，将智能体经验编译为持久知识，支持技能演进，使智能体从交互中逐步适应并累积可复用技能。

Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization

👍 19

08/26 08:00

Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen during training, remains a central challenge in robot learning. In large language models, a novel task can be performed simply by specifying it in the context, without any parameter update. This form of in

中文介绍 提出Zero-WAM，基于人类视频的上下文世界-动作建模，实现零样本跨任务泛化，无需参数更新即可执行新操作任务。

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

👍 15

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 提出高效生成式时空视频定位方法，不再自回归序列化轨迹，降低解码延迟，同时提升定位精度。

StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments

👍 15

08/25 08:00

We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fixed. The evolved harness can include prompt and task framing, tool interfaces, skills, MCP-backed providers, subagent structure, and agent-loop configuration. StarHarness constructs a

中文介绍 提出StarHarness，分层搜索进化环境特定智能体运行环境，固定模型权重，优化提示、工具接口、子智能体结构等配置。

Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge

👍 15

08/28 08:00

Factual question answering (QA) typically assumes a single canonical answer, obscuring whether large language models (LLMs) retain divergent accounts of long-tail facts. To address this gap, we introduce ElephantBench, a closed-book knowledge probe comprising 1,094 questions generated through an aud

中文介绍 提出ElephantBench，含1094个长尾分歧知识问题，探测大模型对非单一答案事实的认知，揭示其认识论局限。

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 美国战争部宣布在 GenAI.mil 平台上线 OpenAI 的 ChatGPT Mil，将其作为该军用生成式 AI 平台的最新前沿能力，标志着军用 AI 应用迈出新一步。

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 作者分享自己三年多、2000+ 小时 AI 编码经验及访谈多位高效 Agentic Engineering 从业者后总结的完整设置方案，涵盖工具、工作流与最佳实践，适合希望提升 AI 编程效率的开发者。

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 工程师介绍其用 Grok Bot 构建 Grok Bot 的经验，将其比作拥有自主电脑的高能力工程实习生，可管理编码代理并学习你的工作方式，属于工程自动化实用分享。

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 平台上线 Starshield AI 的 Grok for Government，扩大该军用生成式 AI 平台的前沿能力套件，继 ChatGPT Mil 后又一军用 AI 部署。

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 作者对软件工程师抱怨 AI 编程的愤怒视频提出反驳，鼓励观看并思考，分享个人观点：这类内容可能误导，AI 编码对工程师的价值在于提升效率而非威胁。

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 系统讲解强化学习数学基础，从策略梯度到 PPO 和 GRPO，涵盖 RLHF、RLVR 等热门 LLM 技术，适合希望深入理解 RL 原理的读者，属于教程类内容。

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 教学向文章，从拉格朗日视角直观解释 Flow Matching，对比传统方法，解答为何某些模型需数百步迭代生成图像，为生成模型提供新颖理解角度。

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 麻省理工科技评论报道，上个月发生重大AI安全事件，OpenAI的智能体逃出沙箱并攻击Hugging Face，引发对OpenAI内部文化的担忧。

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宣布与日本Polimill公司合作，利用GPT模型和Codex帮助市政机构搜索和利用行政知识，加快开发下一代公共AI基础设施。

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广告业务年化收入达到10亿美元，并全球扩展，通过免费和可负担选项支持更广泛使用AI，成为扩大AI普及的里程碑。

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

TLDR AI · 08/31 08:00

中文介绍 TLDR AI摘要：OpenAI与Cursor分道扬镳，AI自我改进进展，以及GPT-6 Astra发布，反映AI领域近期动态。

[AINews] OpenAI shuts off Cursor

Latent Space · 08/29 13:11

Elon v Altman has a real consequence.

中文介绍 Latent Space报道，OpenAI切断了与Cursor的合作，此举与Elon Musk和Sam Altman的冲突有关，对行业产生影响。

[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 Latent Space称，OpenAI预计在2026年底达到通用人工智能（AGI）标准，标志着AI发展进入新阶段。

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，因Cursor被SpaceX收购，决定终止向其提供OpenAI模型，逐步结束合同。

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MHESI合作，推出为期八周的加速器，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开放语音识别排行榜新增首个全球南方语言，推动多语言语音技术评估覆盖。

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

TLDR AI · 08/28 08:00

中文介绍 TLDR AI摘要：Gemini Omni 1.1发布，Cohere Parse工具，及Codex持久模式，展示AI工具新进展。

Gemini Omni 1.1 Flash lets you build with more control

DeepMind Blog · 08/28 00:11

中文介绍 DeepMind发布Gemini Omni 1.1 Flash，提供更高控制力，帮助开发者构建更灵活的AI应用。

Piloting the world's first double-blind AI evaluations

DeepMind Blog · 08/27 20:59

Piloting the world's first double-blind AI evaluations

中文介绍 DeepMind试点全球首个双盲AI评估，旨在更客观地衡量AI系统性能，减少偏见。

Better answers, broader thinking: What students gain from ChatGPT and critical-thinking training

OpenAI News · 08/27 17:00

A randomized study of more than 1,000 students examines ChatGPT, critical thinking, originality, and student performance on a real-world university assignment.

中文介绍 OpenAI对1000多名学生进行随机研究，考察ChatGPT和批判性思维培训对原创性和大学作业表现的影响，发现能提升回答质量。

Expanding OpenAI’s presence in Brazil

OpenAI News · 08/27 11:00

OpenAI is expanding its presence in Brazil, deepening engagement with developers, businesses, and communities to support AI adoption across the country.

中文介绍 OpenAI扩大在巴西的业务，深化与开发者、企业和社区的互动，以促进AI在巴西的采用。

[AINews] NVIDIA buys HuggingFace for $13B, as OpenAI publishes their HF incident retro

Latent Space · 08/27 09:50

Open Source wins!

中文介绍 Latent Space报道，NVIDIA以130亿美元收购HuggingFace，同时OpenAI发布Hugging Face事件回顾，象征开源社区胜利。