2026-09-05

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

👍 213

09/03 08:00

As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what agent post-training actually requires: each can be re-queried into many verifiable tasks and provides execution feedbac

中文介绍 针对终端智能体轨迹丰富但可执行环境稀缺的问题，提出将轨迹转化为可扩展终端环境的方法。每个环境可生成可验证任务并提供执行反馈，为智能体后期训练提供规模化数据支持。

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

👍 139

08/27 08:00

Large language models offer broad capabilities, but adapting them to evolving domains, tools, and requirements often entails repeated post-training. Autonomous systems automate parts of this process by proposing updates, training candidates, and using evaluation feedback to select subsequent proposa

中文介绍 在自主LLM持续后训练中，提出条件经验迁移框架，通过判断何时复用历史经验来避免无效训练。利用评估反馈指导后续提案，提升适应动态环境的效率，减少重复后训练开销。

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

👍 123

09/03 08:00

Large language models achieve superior performance on tasks that require extended reasoning, but long chains of thought make the KV cache a severe memory bottleneck. Existing KV cache compression methods share one paradigm: score each cached token by some estimate of how much it will matter later, a

中文介绍 针对长推理链下KV缓存内存瓶颈，提出Random Attention方法。放弃基于重要性评分的缓存淘汰范式，随机选择需要保留的KV缓存，显著降低内存占用，同时保证推理性能。

Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM

👍 66

09/03 08:00

Hybrid LLMs pair softmax attention with linear-attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the context in fixed size. Early community 4-bit quantizations of Qwen3.8-27B (48 GDN layers, 16 attention layers) left the GDN block in 8- or 16-bit precision -- especially

中文介绍 研究了混合LLM中Gated DeltaNet层为何能承受4比特量化。提出NVFP4 W4A4方案，将GDN层从高位宽降至4比特，在Qwen3.8-27B上保持性能的同时大幅压缩模型尺寸。

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

👍 65

09/03 08:00

On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. Existing work has mainly studied its algorithmic behavior, leaving the role of training data unclear. We examine this role at the data-minimal limit by training on a single query. One-

中文介绍 针对在线蒸馏中训练数据作用不明的问题，在单查询的极端数据限制下进行实验。发现仅一个训练示例即可触发有效的在线教师信号，数据质量比数量更关键。

Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction

👍 34

09/03 08:00

Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed first-frame anchor forces extrapolation far beyond the training distribution. Small drifts accumulate and amplify into significant geometric collapse. However, we observe that per

中文介绍 针对在线3D重建模型在长视频上表现不佳的问题，提出Scal3R方法。通过学习多相对位姿查询替代固定首帧锚点，避免外推累积误差，实现可扩展的在线重建。

Editable Visual Design

👍 32

09/03 08:00

While diffusion base models such as GPT-Image-2 and Nano-Banana exhibit remarkable visual expressiveness, their end-to-end generation inherently yields flattened bitmaps with error-prone text, precluding layer-wise post-editing. Conversely, code-based visual generation via Coding Agents provides pre

中文介绍 提出可编辑视觉设计，结合扩散模型与代码生成智能体，避免纯位图输出不可编辑的缺点。通过代码式生成实现图层化后编辑，降低文字错误并提升用户可控性。

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

👍 29

08/31 08:00

Agent performance depends jointly on the model parameters and the executable harness code that manages context and control flow. Optimizing either component in isolation can leave the system bottlenecked by its frozen counterpart: weight updates can change which harness is effective, while harness u

中文介绍 提出WHALE方法，联合优化智能体的模型参数与可执行代码（harness）。通过简单配方同时更新权重与上下文管理逻辑，打破单一优化带来的瓶颈，提升整体性能。

Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering

👍 26

08/19 08:00

Knowledge-Based Visual Question Answering (KB-VQA) relies on retrieving external information to answer queries involving long-tail entities. However, existing retrieval pipelines predominantly employ CLIP-style dual encoders, which prioritize surface-level visual similarity over entity-level semanti

中文介绍 针对知识型视觉问答中检索过于关注视觉相似度的问题，提出实体对齐检索方法。通过对齐实体语义而非表面视觉特征，提升长尾实体相关信息的检索准确性。

ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

👍 23

09/01 08:00

Compact token sequences are essential for efficient 3D generation. However, existing 3D tokenizers typically organize latent representations either over spatial regions or as fixed-size sets of global tokens, both suffering sharp reconstruction degradation when compressed to extremely low token budg

中文介绍 针对3D生成中压缩到极低token预算时重建质量下降的问题，提出ZipTok3D。利用紧凑token前缀实现高保真3D token化，在极低token数下保持精细结构。

Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding

👍 22

09/03 08:00

Streaming video understanding requires multimodal large language models (MLLMs) to process continuous visual inputs and respond to user queries under strict causality and bounded memory. Existing approaches typically compress historical observations into an external memory bank and retrieve query-re

中文介绍 针对流式视频理解中受限记忆与严格因果性的挑战，提出渐进潜记忆演化机制。无需外部检索，通过动态更新内存，持续压缩历史信息并支持实时查询回应。

CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation

👍 18

09/03 08:00

MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish scenes containing the same concepts but different attribute-object bindings. Yet the same backbone can resolve such distinctions when used as a cross-attentive reranker, motivating us to distill its c

中文介绍 针对多模态嵌入模型组合检索能力不足的问题，提出CORE方法。通过将交叉注意力重排序器的细粒度推理能力蒸馏到嵌入模型中，提升属性-对象绑定的识别，改善组合推理。

DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

👍 17

09/03 08:00

Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work in the outcome-blind setting, where ground-truth success signals are not available. Multi-criteria rubrics are a popular way to supply such a rewar

中文介绍 针对长程智能体任务缺乏可验证奖励的问题，提出DRACO。在无结果反馈设置下，利用动态多标准评分进行细粒度信用分配，指导智能体训练，提高任务成功的可能性。

PACE: Towards Surfacing Hidden Conflicts in User Requests

👍 16

09/03 08:00

Personalized assistants should not only comply with user requests but also assess whether those requests are appropriate given the user's current circumstances. However, prior work has primarily focused on accurately executing requests, overlooking the need for assistants to account for context and

中文介绍 针对个性化助手忽略用户请求中潜在冲突的问题，提出PACE框架。旨在揭示请求与用户当前情境不匹配之处，帮助助手不仅执行指令，还评估其恰当性。

RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests

👍 16

08/31 08:00

Coding agents are now commonly evaluated on the SWE-bench family of benchmarks, whose tasks are built from curated GitHub issues: long, structured, and information-rich. Real user requests, however, are typically far shorter and less structured. To characterize this gap, we define a six-category inf

中文介绍 现实用户请求通常比SWE-bench等基准任务更短且结构差，为此提出RealSWE基准。通过六类信息定义任务，组合式评估编码智能体在真实请求下的表现。

WorldReward: Reward Modeling for Camera-Conditioned World Models

👍 15

09/03 08:00

Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected scene changes while appearance, geometry, and temporal dynamics remain coherent. Existing rewards assess these requirements separately: geometry-based rewards estimate trajectory executi

中文介绍 针对相机条件世界模型的分割奖励问题，提出WorldReward。结合命令执行与场景一致性，统一建模动态与外观，提供更有效的奖励信号。

VibeVoice-ASR-Streaming Technical Report

👍 14

09/02 08:00

Traditional speaker-attributed ASR systems treated ASR and speaker diarization as two separate tasks. Recently, end-to-end models such as VibeVoice-ASR have unified the two tasks within a single model. However, existing unified models still mainly support offline recognition, making it difficult to

中文介绍 报告VibeVoice-ASR-Streaming，端到端流式说话人识别系统。在统一模型中同时处理ASR与说话人日志，支持流式处理，降低离线分发延迟。

Using Grounded Theory for Agent Behavior Analysis at Scale

👍 12

08/31 08:00

Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in long, often unfamiliar tasks where pre-built classifiers fall short. We propose to bring grounded theory into agent trajectory analysis: a six-decade-old qualitative method from the soci

中文介绍 引入扎根理论（grounded theory，一种质性研究方法）用于智能体行为分析。该框架支持对数千条轨迹进行归纳式分析，无需预定义分类器，适合发现长任务中的新模式。

Environment Evolution for Terminal Agents

👍 10

09/03 08:00

Scaling interactive and verifiable environments is critical for training terminal agents. As frontier models become more capable, environments synthesized from scratch become less challenging and thus provide limited learning signals. Recent co-evolution methods iteratively synthesize environments n

中文介绍 针对终端智能体环境可扩展性问题，提出环境进化方法。通过迭代合成并调整环境难度，避免智能体因环境过于简单而缺乏学习信号，提升训练效果。

Principia: Relational Physics Tests for Video Models

👍 10

09/03 08:00

Evaluating physical reasoning in video models is difficult because absolute motion measurements depend on frame rate, object scale, and camera calibration, all of which are often ambiguous or unavailable in generated video. We propose a different approach. When two objects in the same scene obey the

中文介绍 提出Principia基准，通过场景中两物体间的物理关系测试视频模型的物理推理能力。该设计避免了绝对运动测量对帧率、尺度和标定的依赖。

The Cognitive Revolution (When Machines Do The Thinking)

@Konstantine · 17.6K 粉丝 · 256.2K 阅 · 529 赞 · 100 转

09/02 23:07

We externalized our muscles and built the modern world. Now we are externalizing our minds. Most mornings I ride to work in a Waymo. The car is doing physical work: five thousand pounds of metal and

中文介绍 思考：人们外化肌肉力量构建现代世界，如今开始外化思维。作者常乘 Waymo 上班，汽车承担物理工作，而 AI 正接管认知任务，预示认知革命到来，机器将承担思考。

CarryGo, here we go!

@CarryGo_AI · 9 粉丝 · 192.8K 阅 · 1.0K 赞 · 2 转

09/04 18:34

Inside CarryGo lies a world model—helping organizations see, simulate, act and learn as a system. At the product level, CarryGo is a world model, built first for business. At the system level, it is

中文介绍 CarryGo 发布：内置世界模型，帮助组织以系统视角观察、模拟、行动和学习。产品层面面向商业，系统层面则更宏观。强调其世界模型的应用潜力。

Prediction: AI will collapse

@wordgrammer · 26.1K 粉丝 · 120.8K 阅 · 602 赞 · 33 转

09/03 05:30

The dot com bubble got some things right. It noticed that the internet was going to be big. It noticed that the value generated by the internet would roughly scale in proportion with the amount of

中文介绍 预测 AI 将崩盘。类比互联网泡沫：泡沫时对互联网潜力的判断正确，但价值增长与基础设施投入脱节。暗示当前 AI 投资过热，可能重蹈覆辙。

How to design a Brand System from 1 reference image

@AmirMushich · 80.6K 粉丝 · 102.2K 阅 · 501 赞 · 42 转

09/03 00:11

For 10+ years, I've been creating branding & ads for Warner Music, PepsiCo, and others. Now I combine that experience with AI to build hi-end visual systems faster. This article shows my complete

中文介绍 品牌设计师 Amir 结合十年经验与 AI，展示如何从单张参考图设计完整品牌系统。曾服务华纳音乐、百事，现用 AI 加速高端视觉系统构建，分享完整流程。

AI Engineering Skills Map: Using coding agents

@AndrewYNg · 1.9M 粉丝 · 48.9K 阅 · 918 赞 · 136 转

09/04 23:02

A key AI engineering skill is using coding agents. Your skill at steering them both to write code and to carry out non-code tasks, such as analyzing data or managing system operations, allows you to

中文介绍 吴恩达：AI 工程核心技能之一是驾驭编码代理。不仅用于写代码，还能执行分析数据、管理系统运维等非编码任务，掌握此技能可大幅提升工作效率。

Grok Bot for Work

@joshkim · 8.3K 粉丝 · 42.4K 阅 · 525 赞 · 41 转

09/04 06:03

I can't do my job without Grok Bot. It happened really quickly. A few weeks ago, I wasn’t leveraging agents like the AI-pilled experts you see on X and LinkedIn. I was still a human in the loop:

中文介绍 作者分享 Grok Bot 如何成为工作必备。短短几周内，从不用代理到完全依赖，实现了从“人在循环中”到高效利用 AI 代理的转变，甚至无法想象没有它的工作。

Codex has changed my life as a solopreneur

@jonnym1ller · 20.7K 粉丝 · 36.0K 阅 · 510 赞 · 23 转

09/04 06:53

It's difficult to exaggerate how absurdly life-changing Codex has been for me as a solopreneur in recent months. And yet people have been saying 'but what do you actually use it for' (so I decided to

中文介绍 独立开发者盛赞 Codex 彻底改变其生活，难以夸大其影响。针对“你用它做什么”的疑问，决定整理具体用途，展示 Codex 在日常工作中的应用场景。

Introducing Gemini 3.8 Flash and 3.8 Flash Cyber

@GoogleAIStudio · 198.5K 粉丝 · 26.2K 阅 · 507 赞 · 59 转

09/03 00:48

Our newest Gemini models deliver next-generation intelligence for agentic workflows and cybersecurity. Building on the momentum of 3.7 Flash from three weeks ago and marking our third Flash release in

中文介绍 Google AI Studio 发布 Gemini 3.8 Flash 和 3.8 Flash Cyber，面向代理工作流与网络安全，是继 3.7 Flash 三周后的第三款 Flash 模型，持续迭代。

From rg to zg: Local Search Beyond Keywords

@QwenDevs · 10.9K 粉丝 · 21.4K 阅 · 509 赞 · 55 转

09/02 22:30

Summary: The information humans and agents need is often scattered across large numbers of local files, making it difficult to locate accurately and efficiently. zg (zvec-grep) is local-first search

中文介绍 QwenDevs 介绍 zg（zvec-grep）：本地优先的搜索工具，超越关键词匹配。针对人类和代理需要从大量本地文件中精准查找信息的需求，提升搜索准确性和效率。

Architecting memory and storage in the AI era

MIT Tech Review AI · 09/05 02:39

The era of AI inference has arrived. Imagine a healthcare system analyzing millions of data points in real time to accelerate life-saving medical research, or an intelligent assistant instantly resolving thousands of complex customer needs at once. These real-world breakthroughs rely on advanced inf

中文介绍 AI推理时代来临，推动内存与存储架构革新。医疗系统可实时分析数百万数据点加速研究，智能助手能同时处理数千复杂客户需求，这些突破依赖底层基础设施的重新设计。

Data from drones in Ukraine is fueling a new Wild West marketplace

MIT Tech Review AI · 09/04 17:25

Battlefields in Ukraine are littered with the remnants of drones, which are now firmly established as a critical weapon of modern warfare. But behind all that wreckage, there’s a new gold mine for the defense sector. The data drones generate will far outlast the wars in which they are used to fight,

中文介绍 乌克兰战场无人机残骸遍布，其生成的数据远超战争本身寿命，成为国防领域新金矿，催生了一个类似西部荒野的数据交易市场。

[AINews] GPT-6 Astra: OpenAI’s biggest LLM launch of all time

Latent Space · 09/04 13:18

new SOTA computer use and coding, 2.5x pricier per token, but WAY cheaper per task, less monitorable. overall, a very successful launch of OpenAI’s new frontier model class.

中文介绍 OpenAI发布迄今最大规模LLM——GPT-6 Astra，在计算机使用和编码方面达到新SOTA，每令牌价格贵2.5倍，但每任务成本低得多，可监控性降低，整体发布成功。

GPT-6 Astra 🚀, Grok Bot Enterprise 🤖, Runway world model 🌎

TLDR AI · 09/04 08:00

中文介绍 AI新闻摘要：OpenAI发布GPT-6 Astra，Grok Bot推出企业版，Runway发布世界模型，当日三大AI进展。

GPT-6 Astra: an automated AI Engineer you can hire for <$6 an hour

Latent Space · 09/04 05:09

We spent 20B+ tokens of GPT-6 Astra to explore everything. Here’s our learnings.

中文介绍 OpenAI的GPT-6 Astra可视为自动化AI工程师，每小时雇佣成本低于6美元。作者投入超过200亿令牌进行探索，并分享学习心得。

Introducing WeatherNext 3, our most advanced and accurate global weather AI model

DeepMind Blog · 09/03 23:02

中文介绍 Google DeepMind推出WeatherNext 3，宣称是其最先进、最准确的全球天气AI模型，旨在提升天气预报精度。

Daybreak for Frontline Defenders: $1B to protect essential services

OpenAI News · 09/03 21:15

OpenAI introduces Daybreak for Frontline Defenders. A $1 billion commitment expands access to frontier cyber AI, training, and support for essential services.

中文介绍 OpenAI启动“Daybreak for Frontline Defenders”计划，承诺投入10亿美元，扩大前沿网络AI、培训及对关键服务的支持，保护基层防护人员。

NeoMME: an efficient Multimodal-native and Multilingual Encoder

Hugging Face Blog · 09/03 21:13

中文介绍 H公司发布NeoMME，一种高效的多模态原生多语言编码器，旨在提升跨模态、跨语言的理解与处理能力。

Playco cut manual fixes 50% prototyping games with GPT-6 Astra

OpenAI News · 09/03 20:00

Using GPT-6 Astra, Playco built three themed game prototypes from one grey box foundation and reported 50% fewer manual fixes than with the previous model.

中文介绍 游戏公司Playco使用GPT-6 Astra，在灰色盒基础上构建三款主题游戏原型，手动修复减少50%，显示该模型在游戏原型开发中的效率优势。

Legora reviewed 41 documents in minutes with GPT-6 Astra

OpenAI News · 09/03 20:00

Legora used GPT-6 Astra to review 41 documents in minutes, find all four planted errors, and improve performance by nearly 40% in this financial-review workflow.

中文介绍 金融公司Legora利用GPT-6 Astra在数分钟内审阅41份文档，找出全部4处植入错误，财务审查工作流性能提升近40%。

[AINews] Muse Spark 1.3 matches GPT-5.6-Sol, confirming Meta Superintelligence as the newest Frontier Lab, >90% discount for training

Latent Space · 09/03 12:38

an epic comeback story for Meta

中文介绍 Meta发布Muse Spark 1.3，性能匹配GPT-5.6-Sol，证实Meta超级智能成为最新前沿实验室，训练成本折扣超90%，被视为Meta的史诗级回归。

Safety overview: GPT-6 Astra

OpenAI News · 09/03 08:00

GPT-6 Astra is our most capable broadly deployed model and our first to reach the Critical level of cybersecurity capability under our Preparedness Framework.

中文介绍 OpenAI发布GPT-6 Astra安全概览，称其是最强大广泛部署模型，并在其准备框架下首次达到“关键”级网络安全能力。

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

Hugging Face Blog · 09/03 08:00

中文介绍 研究展示如何用GRPO方法在100步内微调350M模型，以生成更好的结构化输出，提升模型对格式的遵循能力。

Give Your Coding Agents a Memory You Own

Hugging Face Blog · 09/03 08:00

中文介绍 文章介绍如何为编码代理提供自主可控的记忆，强调用户拥有记忆的所有权，以提升代理的长期任务表现。

Training a coding model to paint watercolours with TRL and OpenEnv

Hugging Face Blog · 09/03 08:00

中文介绍 教程介绍如何使用TRL和OpenEnv训练编码模型绘制水彩画，展示模型在创意编程任务上的潜力。