2026-09-07

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

👍 276

09/02 20:00

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 随着终端代码代理的普及，代理轨迹大规模累积，但可执行的现实环境仍然稀缺。本论文提出了一种方法，通过合成环境帮助代理在后续训练中生成可验证的任务，并提供执行反馈。该方法解决了现有环境合成技术无法提供足够学习信号的问题，具有重要的应用意义，尤其是在智能体训练和迁移学习的领域。

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

👍 166

09/02 20:00

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 针对大型语言模型在需要较长推理链的任务中面临的KV缓存内存瓶颈，本文提出了“随机注意力”方法，重新思考KV缓存驱逐策略。通过对缓存token进行新的评估，提升了模型在复杂推理任务中的效率。这一研究对于优化长文本生成和推理任务的处理具有重要影响，推动了高效推理的研究趋势。

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

👍 149

08/26 20:00

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 针对大型语言模型在不断变化的领域适应时需频繁进行后训练的问题，本文提出了一种自主更新系统，通过自动提议、训练候选模型并利用反馈选择后续提议，自动化了后训练过程。这种方法的核心在于适应性以及效率优化，具有推动语言模型自适应能力的潜力，对相关应用项目，如交互式助手和自动化工具，具有重要的启示。

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

👍 81

09/02 20:00

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 本文探讨了在只有一个查询示例的情况下，如何在教学模型的密集token级监督下，通过学生生成的回放实现在线策略蒸馏。通过在数据最小化的界限上分析训练数据的角色，提出了新的见解。这一研究对提升语言模型在资源受限条件下的性能具有重要意义，并为自适应和高效模型训练提供了新的思路。

Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

👍 79

09/01 20:00

Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite strong empirical results, these systems lack a unified account of coordination, memory improvement, and the role of external verification. We model orch

中文介绍 针对多智能体面临的任务分解和协调问题，本文提出了一种双层协调反思的方法。通过建立统一的协调框架，模型能够在多智能体系统中有效进行记忆提升和外部验证。研究结果表明，该方法在多智能体协作和推理任务中的表现显著提升，对智能体系统和协作AI的发展有重要影响。

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

👍 74

09/02 20:00

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 本论文分析了混合大语言模型在4位量化中的表现，特别是Gated DeltaNet在处理过程中可以维持256位精度，从而在重采样方面展现出鲁棒性。研究显示，混合模型在参数压缩大幅减少的背景下仍能保证表现，推动了量化技术在大规模模型中的应用，为未来模型压缩与效能提升提供了新的视角。

Iris: Climbing to the Search Frontier

👍 48

09/02 20:00

We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data pipeline and training recipe behind them. Tasks are reverse-constructed from the hyperlink structure of a web corpus: we author multi-hop chains over an entity graph distilled fro

中文介绍 我们提出了Iris-mini和Iris-pro两种搜索智能体，利用网页数据管道进行训练，重构了基于超链接结构的任务。这种方法引入多个跳跃链，通过对实体图的逆向构建，可以提升搜索智能体在实际应用中的性能。该研究为智能体在Web环境中的适应性和效率优化提供了支持，具有广泛的应用前景。

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

👍 46

09/02 20:00

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 在线三维重建模型在处理长视频时表现不佳，主要由于固定第一帧的锚点回归导致的模型外推问题。本文提出了基于每帧信息单独估计相对位姿的方法，有效减少小偏差累积，改善重建准确性。这为三维重建技术的发展和多媒体理解应用提供了新的解决方案，具有重要的工程价值。

Editable Visual Design

👍 42

09/02 20:00

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 本文探讨了基于编码代理的可编辑视觉设计方法，解决了现有扩散基础模型在生成过程中无法进行层级后编辑的问题。通过提供精细的控制，该方法增强了视觉生成的灵活性，为设计和创作领域的智能工具发展提供了新的可能性，推动了可编辑生成模型的研究方向。

Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue

👍 35

08/27 20:00

An avatar that holds a conversation should decide what to say and to move while saying it, yet these abilities live in separate model families: spoken dialogue models produce speech without motion, and co-speech motion models produce motion only from audio handed to them. The standard remedy is a ca

中文介绍 为了实现更自然的对话生成，本文提出了一种联合语音和全身动作的端到端模型，解决了传统模型在对话时缺乏动作生成的问题。研究结果显示，该方法能够更好地协调语音与动作之间的关系，推动了交互式对话系统的发展，为人机交互带来了新的可能。

Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding

👍 30

09/02 20:00

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 流媒体视频理解要求多模态大语言模型处理连续的视觉输入并在有限的内存下响应用户查询。本文提出了进阶潜在内存进化的方法，旨在提高模型在长时链中的有效性。该研究促进了视频理解技术的进步，对智能监控和实时视频处理等领域具有重要的应用价值。

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

👍 29

08/30 20:00

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 本文分析了常用编码代理在面对真实用户请求时的效果与限制，提出了基于六类信息的评估框架以表征用户请求的差异。研究显示，现有基准在短且结构简单的真实请求生成中存在不足。这为提高编码代理的适应性与实用性提供了方向，并对人机交互研究具有重要的启示。

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

👍 25

09/02 20:00

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 本文提出了DRACO框架，采用动态评估标准为长期智能体训练提供精细的信用分配。即使在缺乏真实结果信号的情况下，仍然能够通过多标准量表提供有效反馈。这一研究对强化学习中的奖励设计和长期任务的智能体培训具有重要影响，推动了长期智能体训练的研究进程。

CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation

👍 25

09/02 20:00

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 针对多模态大语言模型在组合检索中的限制，本文提出CORE方法，该方法通过再排序蒸馏提升了嵌入模型在场景区分中的能力。研究显示，该方法能够显著提高检索答案的准确性，推动了组合推理和检索模型的研究与应用，具有重要的实用价值。

WorldReward: Reward Modeling for Camera-Conditioned World Models

👍 24

09/02 20:00

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 本论文提出了Camera-conditioned world models用于生成互动视频，要求预设的动作引发预期的场景变化。通过将几何、外观和时序动态纳入奖励机制，改进了现有模型的评估方法。这项研究对于生成互动内容和虚拟现实的场景控制提供了新的视角，推动了基于视觉的智能体技术的发展。

PACE: Towards Surfacing Hidden Conflicts in User Requests

👍 23

09/02 20:00

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 为了解决个性化助手在执行用户请求时的适应性，本论文强调了助理需考虑用户当前情境的必要性。通过提出关联冲突的评估框架，研究探索了助手在执行请求时的环境适应性，促进了个性化服务优化的研究，具有重要的应用潜力。

Using Grounded Theory for Agent Behavior Analysis at Scale

👍 19

08/30 20:00

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 为了理解智能体行为，本文提出了引入基础理论来分析大量轨迹中的行为模式。通过定性方法，研究能够在长任务中发现新的模式，弥补了现有分类器的方法不足。这一研究为理解复杂智能体行为的生成机制提供了新的视角，推动了智能系统解释性和透明性的研究方向。

Environment Evolution for Terminal Agents

👍 18

09/02 20:00

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 本文讨论了终端智能体在环境合成中的进化问题，提出了一种方法使环境与智能体的能力相匹配，以提供有效的学习信号。通过协同发展环境和模型，提升了合成环境的挑战性，改善了训练效果。这一进展对于终端智能体的训练和多样性学习具有重要的推动作用，未来在代理模型的提升方面具有深远意义。

The Attention Triangle in Audio-Video Models

👍 16

09/02 20:00

Audio-video diffusion models rely on cross-modal attention to coordinate text, sound, and visual content, yet this same mechanism can introduce subtle and systematic semantic leakage. We study these models by probing and analyzing the ``attention triangle,'' comprising the three cross-attention edge

中文介绍 本文研究了音视频扩散模型中的“注意力三角”效应，揭示了跨模态注意力在文本、音频和视觉内容协调中的作用，同时也可能造成语义泄露。通过深入分析该机制，研究为改善多模态模型的表现提供了指导，推动了音视频内容生成和处理的研究发展，对多模态学习有重要的启示。

Principia: Relational Physics Tests for Video Models

👍 16

09/02 20:00

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 在评估视频模型的物理推理能力时，依靠绝对运动测量的困难带来了挑战。本文提出了一种新的方法，通过分析同一场景中两个物体的相对运动，绕过了传统依赖帧率和相机校正的问题，为物理推理的有效性评估提供了新的途径。这一研究推动了视频理解和物理推理的结合，具有重要的应用价值。

Grok Imagine Odyssey Contest Winners

@imagine · 79.2K 粉丝 · 714.5K 阅 · 532 赞 · 86 转

09/04 16:49

Homer had a lyre. You had Grok Imagine. Thousands of you quoted our launch post and built original Odyssey scenes in Grok Imagine. Image, video, and the voices. Three to five minutes, with at least

中文介绍 博主分享了 Grok Imagine 大赛的获奖作品，展现了大家在 Grok Imagine 中构建原创关卡的创意场景。参赛者们以图像、视频和声音形式进行创作，时间限制在三到五分钟，充分体现了 AI 工具在创作中的潜力。

Five things I learned from using Astra

@dkundel · 23.9K 粉丝 · 225.2K 阅 · 520 赞 · 44 转

09/04 16:27

Back in February, getting Codex to build LEGO models took a custom skill, complicated instructions, and hours of iteration. And it was still not great. I came away thinking it wasn’t something models

中文介绍 博主总结了使用 Astra 的经验，回顾在构建 LEGO 模型时遇到的挑战和复杂性。他认为 Codex 的初期使用效果不佳，而 Astra 能在此过程中带来显著改善和效率提升，反映了 AI 工具的演变与发展。

Claude Code → Codex (and keep everything you already built)

@charliejhills · 14.1K 粉丝 · 120.8K 阅 · 504 赞 · 53 转

09/06 06:44

For months people have been telling me Codex is better than Claude Code. I ignored all of it. I have built my whole business inside Claude Code (every pipeline, every system) and I did not fancy

中文介绍 博主讨论了 Codex 与 Claude Code 之间的优劣比较，尽管他一直使用 Claude Code 构建业务流程，但他开始考虑切换到 Codex，以获得更好的性能和功能支持，揭示了广大用户对工具选择的关注。

Applied AI Doesn't Work

@vasuman · 96.1K 粉丝 · 109.9K 阅 · 517 赞 · 32 转

09/04 18:17

The world has spent a fortune on AI. For most enterprises, nothing changed. I've spoken to over 300 CEOs, CIOs and CFOs at the largest companies on Earth. I learned most companies apply AI onto their

中文介绍 博主指出，尽管企业在 AI 投资上花费了巨额资金，但实际上许多公司的 AI 应用并未带来预期的改变。他与多位高管的交流体现了对 AI 实际效果的质疑，反映出行业中的困惑与挑战。

SARVAM AI Interview Experience and Prep - Backend Engineer (On-Device AI) Internship:

@buzzy_bit · 767 粉丝 · 97.5K 阅 · 500 赞 · 20 转

09/05 03:30

Disclaimer: This post is written purely to share my experience and the way I prepared. It is not a leaked question bank, I'm intentionally not reproducing exact interview questions, and I'm not naming

中文介绍 博主分享了自己的面试经验和准备过程，包括针对后端工程师实习的准备工作。虽然没有泄露具体问题，但他强调了准备过程中的要点，为其他求职者提供了参考，揭示了面试流程透明度的提升。

How I make content with Astra

@nickbaumann_ · 20.0K 粉丝 · 74.8K 阅 · 511 赞 · 38 转

09/04 16:37

I've been using Astra in Codex to edit videos we've shipped on the official ChatGPT Instagram. I've also been using it to pull clips from longer videos and create product animations. And what's really

中文介绍 博主展示了如何利用 Codex 中的 Astra 进行视频编辑，重点介绍了从长视频中提取片段和创建产品动画的过程。这一实践表明 AI 在内容创作中的有效应用，推动了视频制作的新潮流。

AI Engineering Skills Map: Using coding agents

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

09/04 11:02

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 博主指出，掌握代码代理的技能是 AI 工程师的重要能力，包括如何引导它们编写代码和执行数据分析等非编码任务。这一观点强调了复合型技能在 AI 领域中的重要性，接纳快速发展的行业趋势。

Rethinking skills and prompts for GPT-6 Astra

@pvncher · 35.4K 粉丝 · 44.6K 阅 · 508 赞 · 37 转

09/04 17:44

Coding agents have come a long way, and best practices are changing fast. What used to require a lot of handholding and scaffolding no longer does. If you’ve been using agents in your projects over

中文介绍 博主讨论了针对 GPT-6 Astra 的技能和提示的重新思考，指出过去需要大量手动协助的情况如今已经有所改变。这反映了编码代理快速发展的现状和最佳实践的持续演变，体现了行业的快速适应能力。

Supporting independent journalism in Ukraine

OpenAI News · 09/06 20:00

OpenAI, AIRPPU and WAN-IFRA launch an AI program to help Ukrainian news organizations strengthen innovation, resilience, and independent journalism.

中文介绍 OpenAI、AIRPPU 和 WAN-IFRA 联合推出了一项人工智能项目，旨在帮助乌克兰新闻机构增强创新能力、韧性和独立新闻报道。

Claude proves Fermat 🧮, automated AI researcher 🔬, Z1 efficiency chip ⚡

TLDR AI · 09/06 20:00

中文介绍 Claude 证明了 Fermat 理论，推动了一项自动化人工智能研究的发展。

An Alien Mind

OpenAI News · 09/06 05:00

Jakub Pachocki reflects on increasingly capable AI and the challenge of keeping it aligned. He calls for stronger safeguards and international coordination.

中文介绍 Jakub Pachocki 反思了在日益强大的人工智能面前，保持其对齐的挑战，并呼吁加强保护措施和国际协调。

Research acceleration: The view inside OpenAI

OpenAI News · 09/06 04:00

Inside OpenAI, coding agents are reshaping AI research. Explore early data on agent usage, experiment velocity, task complexity, and research acceleration.

中文介绍 OpenAI 内部的编码代理正在重塑人工智能研究，推动实验速度、任务复杂性和研究加速。

OpenClaw Power, MacBook Simplicity: Five Days With Grok Bot

Latent Space · 09/05 11:01

SpaceXAI’s Grok Bot has the same level of programming power as OpenClaw, but it’s programmable at a different level of abstraction.

中文介绍 SpaceXAI 的 Grok Bot 具备与 OpenClaw 相同水平的编程能力，但可在不同抽象级别下进行编程。

Architecting memory and storage in the AI era

MIT Tech Review AI · 09/04 14:39

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 在人工智能推理时代，想象一个医疗系统能够实时分析数百万数据点，以加速救生医学研究。

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

MIT Tech Review AI · 09/04 05:25

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 乌克兰战场上遍布无人机残骸，成为现代战斗的重要武器，同时为国防部门创造出新的数据市场。

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

Latent Space · 09/04 01:18

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 推出的 GPT-6 Astra 是迄今为止最大规模的语言模型发布，价格为每个令牌高出 2.5 倍，但每项任务的成本显著降低。

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

TLDR AI · 09/03 20:00

中文介绍 GPT-6 Astra、Grok Bot 企业版和 Runway 世界模型的相关信息被发布。

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

Latent Space · 09/03 17:09

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

中文介绍 GPT-6 Astra 成为一个自动化的 AI 工程师，供雇佣，时薪不到 6 美元。

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

DeepMind Blog · 09/03 11:02

中文介绍 DeepMind 发布了他们最先进和准确的全球天气人工智能模型 WeatherNext 3。

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

OpenAI News · 09/03 09:15

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 向 Frontline Defenders 承诺投资 10 亿美元，以扩展对前沿网络 AI、培训和基本服务的支持。

NeoMME: an efficient Multimodal-native and Multilingual Encoder

Hugging Face Blog · 09/03 09:13

中文介绍 发布了 NeoMME：一个高效的多模态原生和多语言编码器。

Legora reviewed 41 documents in minutes with GPT-6 Astra

OpenAI News · 09/03 08:00

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 Legora 使用 GPT-6 Astra 在几分钟内审核了 41 份文件，发现了所有四个伪造错误，提升了近 40% 的财务审核效率。

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

OpenAI News · 09/03 08:00

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 Playco 利用 GPT-6 Astra 构建了三个主题游戏原型，报告显示手动修复减少了 50%。