2026-09-22

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

👍 146

09/17 08:00

The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expensive, and large KV caches continue to strain HBM and SSD capacity and data-transf

中文介绍 DeepSeek-V4.1-Flash面向长上下文Agent工作负载的KV Cache压缩，目标降低长输入下prefill计算成本，并缓解大规模KV Cache对HBM、SSD容量与数据传输的瓶颈，推进KV Cache压缩技术的上限。

Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model

👍 116

09/16 08:00

Recent Omni-Modal Generative Models (Omni-Models) have advanced content generation toward unified modeling of text, images, video, and audio. MiniMax-H3 exemplifies this transition by combining multimodal context understanding with joint audio-visual generation in a shared latent framework. Its unif

中文介绍 本文评估MiniMax-H3等全模态生成模型是否能理解物理世界。MiniMax-H3在同一潜在框架下统一建模文本、图像、视频和音频，支持多模态上下文理解与联合视听生成。

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

👍 96

09/17 08:00

We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even exhaust the generation budget. We identify termination-token mismatch between base students and post-trained teachers as an important source of this behavior. Across Qwen3, Llama,

中文介绍 研究on-policy distillation中常见的长度膨胀问题，即学生模型输出过长甚至耗尽生成预算。作者将其归因于学生与教师终止token不一致，并在Qwen3、Llama等模型上展开分析。

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

👍 88

09/18 08:00

Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-source codebases offer a rich source of such tasks, while existing methods typically rely on development artifacts such as issues and commits, limiting the range of tasks that can be e

中文介绍 CodeMidas提出从开源代码库自身构造用于编码Agent强化学习训练的大规模环境。不同于依赖issue、commit等开发产物，该方法能自动产出更多样化的任务及可靠验证器。

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

👍 86

09/04 08:00

Reusable skills give agents transferable procedural knowledge, making scalable acquisition essential for extending agents beyond prior experience. Existing methods face two limitations: trajectory-based synthesis requires interactions with specific environments, while document-derived skills may lac

中文介绍 针对Agent可复用技能的规模化获取问题，提出基于代码的大规模技能合成方法。相比轨迹式合成需特定环境交互、文档式技能可能缺乏过程性知识，该方法更具可扩展性与可操作性。

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

👍 69

09/14 08:00

Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a challenging agent-data gap: heterogeneous data resides outside the agent, while the agent can access it (e.g., column names and file paths) only throu

中文介绍 EvoOntology为数据Agent构建自演化本体层，缓解Agent与异质数据之间的鸿沟。通过让Agent能访问数据中的表名、字段名、文件路径等结构信息，提升对表格、文件、数据库的NL指令执行能力。

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

👍 60

09/18 08:00

Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both, interleaved rather than stacked end to end. We study hybrid CUAs that autonomously decide when to explore an interface

中文介绍 RecreationWorld为混合式computer-use agent构建可扩展且可验证的训练环境，支持图形界面交互与代码/命令行软件开发的交错执行，使Agent能自主决定何时探索界面。

JEPA-Anything: Learning Predictive Models across Different Worlds

👍 58

09/17 08:00

World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning principle support world modeling across radically different systems? We introduce JEPA-Anything, a domain-agnostic fram

中文介绍 JEPA-Anything提出领域无关的预测建模框架，用统一学习原则支持跨系统的世界建模。目标是使智能体能在不同世界中预测结果、指导干预并从交互中学习。

Verifiable Social Reasoning for LLM Assistants

👍 51

09/15 08:00

LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where the assistant learns about social situations from subjective user narratives, and (ii) social properties, such as others'

中文介绍 提出可验证的社会推理评测方法，用于评估LLM助手在日常社交咨询场景中的表现。难点在于需从主观用户叙述中理解情境，并对他人意图等社会属性进行可验证判断。

Self-Evolving Search Index

👍 47

09/17 08:00

Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. Because retrieval relies on an index that represents each document through index keys, retrieval quality depends heavily on how effectively these keys expose the knowledge containe

中文介绍 提出Self-Evolving Search Index，面向LLM Agent的信息检索需求。通过动态改进文档索引键的表达能力，使索引更充分暴露文档中的知识，从而提升复杂任务中的检索质量。

RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation

👍 42

09/15 08:00

Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundant symbols, then route users through disguised links to services associated with pornography, fraud, gambling, or illicit transactions. Existing benchmarks evaluate obfuscated text

中文介绍 RiskChainBench评测被混淆的平台消息还原与基于证据的网页调查能力。平台滥用活动常用emoji、同音字、拆字、冗余符号隐藏跳转指令，并将用户导向涉黄、诈骗、赌博等非法服务。

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

👍 41

09/17 08:00

Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-level supervision from a self-teacher with privileged task skills, letting a skill-free student internalize them. This rec

中文介绍 RetireOPD提出自退场式on-policy distillation，用于Agentic RL训练。相比每条轨迹仅有单一标量奖励，OPD提供token级密集监督；本文通过自退场机制缓解自教师带来的问题。

Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

👍 38

09/15 08:00

GUI agents execute long-horizon tasks on dynamic graphical user interfaces, where pop-ups, delayed loads, and relocated widgets routinely invalidate plans fixed before execution. Recent agent-skill frameworks encapsulate reusable procedural knowledge to mitigate this, yet existing skill designs are

中文介绍 提出免训练的GUI Agent技能演化方法。通过反思、修订与复用机制，使技能框架能自适应应对弹窗、延迟加载、控件移位等动态界面变化，提升长程GUI任务执行效果。

WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing

👍 35

09/17 08:00

Document parsing converts document images into structured content and requires reliable performance across diverse layouts and acquisition conditions. Yet training corpora are biased toward common document types and clean digital pages, while expanding coverage alone does not specify how to address

中文介绍 WeVisDoc面向端到端文档解析，从覆盖度转向能力评估。针对训练语料偏向常见文档类型与干净数字页面、单纯扩展覆盖无法解决难题的问题，提升多样版式与采集条件下的解析能力。

When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models

👍 33

09/17 08:00

Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they often overthink easy problems and underthink hard ones. Existing approaches based on uniform length penalties or rigid routing incur an efficiency tax, trading reduced computation on e

中文介绍 When2Think研究混合推理模型中基于难度的长度控制。针对大型推理模型在简单题过度思考、难题思考不足的问题，提出动态长度策略，避免统一惩罚或刚性路由带来的效率代价。

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

👍 30

09/18 08:00

We define OmniVChat (Omni Video Chat) as the task of native audio-visual dialogue between a user and an omni model. In OmniVChat, omni models directly and simultaneously receive audio and video from a user and return text. The user's query is embedded in the audio and video, without a separate text

中文介绍 OmniVChat定义原生视听对话任务：全模态模型同时直接接收用户音频和视频并返回文本，查询嵌入于音视频中而非独立文本。本文完成数据合成、基准构建与模型训练。

What Does Privileged Information Add to On-Policy Self-Distillation?

👍 30

09/17 08:00

On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher this extra information seems to offer the student more to learn, but how much does it add beyond distillation itself? To isolate that contribution,

中文介绍 本文研究特权信息在on-policy self-distillation中的增量贡献。OPSD让语言模型从持有答案或解题过程的冻结自身学习，作者分离其相对普通蒸馏额外提供的收益。

UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation

👍 30

09/17 08:00

Multi-modal image generation, particularly subject-driven customization, has garnered growing attention in recent years. Despite the rapid advancement of generative models, their evaluation remains largely lagging. Existing methods, whether embedding-based or Multi-modal Large Language Model (MLLM)-

中文介绍 UFO提出面向多模态图像生成的全条件对齐链式评估方法。针对主体驱动定制生成中评估滞后于生成能力的问题，超越基于嵌入或MLLM的现有方法，进行多条件联合评价。

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

👍 29

09/17 08:00

Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation, editing, and colorization, but often relies on dedicated color representations or specialized inferenc

中文介绍 Paint-Anything提出统一任意颜色控制框架，支持用任意24-bit十六进制颜色值指导图像生成与编辑。不同于以往依赖专门颜色表示或专用推理流程的方法，实现专业化设计的精准着色。

Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling

👍 29

09/16 08:00

Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses. In sampling-based methods, the inference budget is often described by the number of generated candidates, N. However, N tells us how many candidates are generated, not how they are

中文介绍 研究LLM测试时扩展中候选生成策略对能耗与性能的影响。指出仅以候选数量N描述推理预算不充分，应关注候选如何生成，不同采样策略下成本与收益差异显著。

You're Already a Meat Proxy

@obie · 13.1K 粉丝 · 157.2K 阅 · 738 赞 · 98 转

09/21 05:02

I’m excited about a future that I suspect will be very hard on many long-time friends and certain people that I love. The same technology that is allowing me to be more successful than ever is

中文介绍 对 AI 冲击的思考：作者认为当前技术让自己比以往更成功，但同时预感这将让许多长期朋友和熟悉的人陷入艰难处境，呼吁正视 AI 带来的现实影响。

I reverse-engineered Instinct's memory. Here's exactly how it works

@DhravyaShah · 62.1K 粉丝 · 120.2K 阅 · 509 赞 · 16 转

09/21 02:49

Instinct has taken the world by storm over the last two weeks - it's one of the best imessage assistants I've used. as with every product, I decided to reverse-engineer Instinct's memory to find out

中文介绍 作者逆向工程了 iMessage 助手 Instinct 的记忆机制，解析其工作原理。作为近两周口碑最好的 iMessage 助手之一，该分析对开发类似产品有参考价值。

Codex vs Claude for app development

@twostraws · 120.7K 粉丝 · 77.1K 阅 · 504 赞 · 42 转

09/19 22:30

I use both Codex and Claude for app development work, both with the highest-tier subscription. Here's how I've found the two compare, plus some tips for success… TL;DR I use both agents extensively,

中文介绍 作者同时用最高订阅档的 Codex 和 Claude 做 App 开发，对比两款 AI 编码代理的优劣，并分享成功经验提示，为开发者选型提供参考。

A Beginner's Guide to Jev

@omarsar0 · 320.6K 粉丝 · 73.5K 阅 · 523 赞 · 60 转

09/21 04:44

As you may have seen recently, Jev (a generalist System One model) took Twitter by storm. Many misleading examples are everywhere, but they don't really show Jev's real capabilities. Hence, we

中文介绍 面向新手的 Jev 入门指南。作者指出网上流传的 Jev 案例多为误导，无法体现其真实能力，故写此指南帮助理解这一通用 System One 模型的实际水平。

Jev, System One models, and the future of computer use

@trycua · 19.0K 粉丝 · 59.5K 阅 · 501 赞 · 39 转

09/20 06:27

What we've been building with decision models at Cua - by @ddupont808 and @francedot Over the last few days we've deprioritized some other shiny objects because we've all been Jev-crazy. TypeSafe

中文介绍 Cua 团队分享在决策模型上的构建经验，聚焦 Jev、System One 模型与计算机使用的未来方向，探讨其在 TypeSafe 等场景中的潜力。

How to Use Jev to Build a 24/7 HFT Trading System

@RohOnChain · 72.5K 粉丝 · 57.7K 阅 · 518 赞 · 54 转

09/19 22:05

I will break down the exact framework to build a millisecond speed 24/7 HFT trading system with Jev, along with the exact resources that helped me personally. Let's get straight to it. Bookmark This -

中文介绍 作者分享用 Jev 搭建毫秒级、24/7 高频交易系统的完整框架，并附上相关资源，为量化交易开发者提供可落地的实践路径。

Jev-as-a-Judge for Agent Evals

@LangChain · 265.9K 粉丝 · 46.6K 阅 · 504 赞 · 68 转

09/20 07:31

By Daniel Shea and Seán Roche Key takeways: Jev is a fundamentally different kind of evaluator. It returns typed answers directly instead of generating text like an LLM judge. Jev was dramatically

中文介绍 LangChain 团队提出 Jev-as-a-Judge 方案用于 Agent 评估。Jev 返回类型化答案而非文本，作为评判器表现显著优于传统 LLM judge。

Jev 101: what it is, and what you can build with it

@manish_fp · 846 粉丝 · 44.1K 阅 · 512 赞 · 59 转

09/19 22:59

I have read 10+ articles, watched 5 hours of content to understand what actually Jev is and then chose to write this. It is not a chatbot, It’s a whole new kind of AI, more like a classifier which

中文介绍 Jev 101 科普文。作者综合十余篇文章、五小时内容后总结：Jev 不是聊天机器人，而是一种新型 AI，更接近分类器，可构建多种应用。

Build your own Jev (100% local)

@_avichawla · 77.5K 粉丝 · 37.8K 阅 · 593 赞 · 80 转

09/20 14:46

Everything you need to turn an open-source LLM into a fast, local decision engine without retraining it. It covers next-token scoring, fixed choices with probability distributions, SGLang, and a

中文介绍 教程：100% 本地化构建 Jev。覆盖 next-token 评分、固定选择概率分布、SGLang 等技术，无需重训练即可把开源 LLM 变为快速本地决策引擎。

A Swarm of Fruit Flies, Building a Civilization On-Chain

@murmur_arc · 983 粉丝 · 11.8K 阅 · 553 赞 · 137 转

09/20 21:17

Prologue — No LLMs, Only Neurons This project is called murmur, and it is alive right now on Arc mainnet (Chain ID 5042), settling in real USDC. To date the flies have completed more than 23,000

中文介绍 项目 murmur 在 Arc 主网运行，不用 LLM 仅靠神经元让一群果蝇在链上建立文明，已完成超 23,000 次结算，使用真实 USDC。

Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI

Latent Space · 09/22 06:13

The definitive Jev podcast with its lead creator.

中文介绍 Latent Space 播客发布 Jev 系列权威访谈，受访人为 TypeSafe AI 首席执行官 Diogo Almeida，聚焦面向生产环境的 System One 模型，而非通用大模型。

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

Hugging Face Blog · 09/21 21:44

中文介绍 Hugging Face 博客介绍一种物理学家风格的 LLM 剪枝方法，将模块移除建模为 Ising 优化问题，用于在保留性能的同时压缩大语言模型。

Advisory Group on Mathematics and Artificial Intelligence

OpenAI News · 09/21 20:00

OpenAI is working with an independent Advisory Group on Mathematics and Artificial Intelligence to guide the review and communication of emerging AI results.

中文介绍 OpenAI 宣布成立独立的数学与人工智能顾问组，协助审查并对外沟通新兴 AI 研究成果，以支撑其研究与安全相关工作。

Higgsfield AI ships new video features in a day with GPT-6 Astra

OpenAI News · 09/21 20:00

With GPT-6 Astra, Higgsfield AI makes video ad creation easier for small businesses and brings new creative tools to market faster.

中文介绍 Higgsfield AI 借助 GPT-6 Astra，在一天内推出新的视频功能，降低小企业制作视频广告门槛，并加快创意工具的上市速度。

How we made the first comprehensive map of deaths along the US border’s “virtual wall”

MIT Tech Review AI · 09/21 20:00

Our 15-month investigation into death and surveillance along the US-Mexico border began with a simple question: Why did so many people die near government surveillance towers meant to help track and apprehend them? This story is part of Dying on Camera, a collaboration between MIT Technology Review

中文介绍 MIT 科技评论公布 15 个月调查，首次绘制美国边境「虚拟墙」沿线死亡事件地图，质疑本应辅助追踪的监控塔为何仍有许多人遇难。

4 ways to address the failures we found along the US border’s “virtual wall”

MIT Tech Review AI · 09/21 20:00

MIT Technology Review today published our investigation into how many people have died near the “virtual wall” of surveillance towers that the US government has installed along the US-Mexico border. We found cases of people who walked undetected through areas surveilled by advanced, AI-enabled tower

中文介绍 MIT 科技评论提出四项政策建议，以应对美国美墨边境「虚拟墙」监控失效问题，调查发现有人员未经检测即穿过高级监控区域。

The US spent billions on border surveillance. Why can’t it catch people before they die?

MIT Tech Review AI · 09/21 20:00

When José Morales Bernal crossed the border into the United States on April 8, 2024, the day before his 32nd birthday, it should have triggered a chain of technological alerts and human responses. As he walked through the desert in southern New Mexico that morning, he was within range of three surve

中文介绍 MIT 科技评论调查显示，美国投入数十亿美元部署边境监控后，仍未能及时预警人员死亡，以新墨西哥沙漠中 José Morales Bernal 遇难案例为例。

She died at the San Diego border. A surveillance camera was in plain sight

MIT Tech Review AI · 09/21 20:00

She had only walked for a couple of hours, and already she was lost. It was early afternoon on Sept. 14, 2025, when 30-year-old Graciela Gómez Hernández crossed the border from the eastern edge of Tijuana into Southern California, sending voice messages to her mother and sister as she walked. This s

中文介绍 MIT 科技评论报道，30 岁的 Graciela Gómez Hernández 于 2025 年 9 月 14 日从蒂华纳越境进入加州后死亡，附近即有监控摄像头，却未被及时识别。

Building standards for the next phase of AI

OpenAI News · 09/21 18:00

OpenAI outlines a path to shared global AI standards, calling for coordinated evaluation, reporting, and governance to improve safety.

中文介绍 OpenAI 提出下一阶段 AI 的标准化路径，呼吁全球协同推进评估、报告与治理机制，以提升人工智能安全性。

Expanding OpenAI Academy with new learning paths

OpenAI News · 09/21 15:00

Explore new OpenAI Academy learning paths for employees, developers, leaders, educators, and students to build and demonstrate practical AI skills.

中文介绍 OpenAI Academy 新增多条学习路径，面向员工、开发者、领导者、教育工作者及学生，用于培养与展示实用 AI 技能。

How V7 gives AI agents institutional memory

OpenAI News · 09/21 08:00

Using GPT-5.6, V7 turns scattered company files into context agents can use to complete complex, source-linked work.

中文介绍 OpenAI 发布 V7 产品说明，借助 GPT-5.6 将分散的公司文件转化为可供智能体使用的上下文，为 AI 智能体提供机构记忆能力。

tokenizers v1: encode, decode and scaling, measured

Hugging Face Blog · 09/21 08:00

中文介绍 Hugging Face 博客发布 tokenizers v1 版本更新，对编码、解码与规模化性能进行实测，提供量化对比数据。

Muse connectors 🤖, Meta SAM 3.1 🖼️, Gemini hacks companies 🔓

TLDR AI · 09/21 08:00

中文介绍 TLDR AI 于 2026 年 9 月 21 日汇总 AI 行业动态，涵盖 Muse 连接器、Meta SAM 3.1 模型发布，以及 Gemini 被利用攻击企业的漏洞案例。

[AINews] Here are 6 Clones of Jev in 2 days

Latent Space · 09/19 13:48

Imitation is the sincerest form of Flattery

中文介绍 Latent Space 的 AINews 报道，仅用两天时间即出现 6 个 Jev 的克隆模型，引发对模型复制速度和原创性边界的讨论。

Introducing the Australian Youth Safety Blueprint

OpenAI News · 09/18 20:00

OpenAI introduces the Australian Youth Safety Blueprint, a six-pillar roadmap for safer AI experiences that protect and empower young people.

中文介绍 OpenAI 推出澳大利亚青少年安全蓝图，以六大支柱规划更安全的人工智能体验，旨在保护并赋能青少年用户群体。