2026-09-03

StudentSim: Training LLM-based Student Simulators

👍 458

09/01 08:00

AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulators can provide this signal as a proxy, yet existing approach

中文介绍 提出训练基于LLM的学生模拟器StudentSim，以补充真实学习者数据稀缺的问题。利用真实对话和错误模式生成模拟学生，支持个性化辅导策略评估。相比现有方法，能更真实地反映学生行为，为自适应教学提供代理信号。

UI-Venus-2 Technical Report

👍 55

08/27 08:00

Multimodal GUI agents have emerged as a promising paradigm for digital task automation, yet transitioning from benchmark-oriented models to dependable real-world applications remains challenging due to limited environment coverage, brittle task construction, and unreliable reward verification. In th

中文介绍 针对多模态GUI代理从基准测试到真实应用部署的挑战，提出UI-Venus-2技术报告。通过扩展环境覆盖、稳健任务构建和可靠奖励验证，增强代理的泛化能力。在多种GUI任务上达到领先性能，推动数字任务自动化落地。

From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix

👍 31

09/01 08:00

Data-residency constraints force enterprises to self-host LLMs, but continuous adoption of newer models without decommissioning their predecessors expands the serving fleet, fragmenting a finite GPU pool. We consolidate traffic from over 200 internal applications onto a single model by closing quali

中文介绍 为解决企业数据驻留限制导致的多模型部署碎片化问题，提出将200多个内部应用流量整合到单一自托管LLM。通过后训练阶段的质量差距闭合，在满足合规的同时优化GPU利用，实现模型集约化管理。

SHAPE of Chain-of-Thought in Math Reasoning

👍 27

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，从数学结构视角分析LLM在数学推理中思维链（CoT）的形态。通过两个维度刻画推理轨迹，揭示模型深层数学技能，为提升推理可解释性和性能提供新方法。

Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering

👍 26

08/31 08:00

A central bottleneck in multi-hop Question Answering (QA) is that the granularity at which a question is expressed often differs from the granularity at which corpus evidence is retrievable. Existing methods address this mismatch by imposing fixed graph structures over the corpus, by iteratively ref

中文介绍 针对多跳问答中问题粒度与语料证据不匹配问题，提出层级证据引导的查询细化方法Hi-Q。利用证据层级结构，迭代细化问题，无需固定图结构，显著提升多跳问答准确性。

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation

👍 26

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 旨在激发VLM内在空间智能用于通用具身导航。提出LightNav-0，将视觉语言模型的空间先验转化为导航动作，跨任务和环境泛化，无需额外训练。在多个导航基准上表现优异。

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

👍 25

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 针对多应用代码库的联合生成与维护，提出Super Library Agent方法。在应用间共享逻辑的基础上，实现代码库的统一管理。相比独立生成，减少重复工作并提升维护效率。

Evaluating the Hidden Costs of Personalization in Large Language Models

👍 25

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 系统评估个性化信号对LLM输出的影响，揭示个性化在提升满意度的同时可能牺牲信息平衡。通过对比有无个性化条件下的回复质量，量化其隐性成本，为设计负责任的个性化LLM提供依据。

Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching

👍 21

09/01 08:00

Multimodal Large Language Models (MLLMs) are strong perceivers of images and video. We ask how far that reach extends into acting: dropping an MLLM directly into a drone's control loop, with its entire action space declared solely in the prompt. Recent systems approach this setting but increasingly

中文介绍 研究MLLM作为通用视觉-语言-动作代理直接嵌入无人机控制环的可行性。在提示中仅声明动作空间，评估其在指挥、接近、跟踪和搜索任务上的能力，探索多模态模型在具身控制中的潜力。

AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling

👍 16

08/27 08:00

LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely unexamined. We present AgentJudgeBench, the first benchmark to systematically study LLM-as-a-judge reliability for agentic tool-calling over workflow

中文介绍 提出多难度基准AgentJudgeBench，首次系统研究LLM评判者在代理工具调用工作流上的可靠性。覆盖从简单到复杂的依赖型任务，揭示评判模型的优势与局限，为开发可靠评判者提供参考。

DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory

👍 14

09/01 08:00

Self-play is an effective paradigm for language-model self-evolution, but without guidance, solver performance can plateau or decline across rounds. Unguided methods steer question generation with signals such as difficulty, learnability, or diversity. These signals keep questions challenging and va

中文介绍 提出DiagEvo，一种基于诊断引导和层级错误记忆的自我进化框架。通过记录并利用错误模式，指导问题生成与求解，避免无引导方法中的性能停滞或下降，持续提升模型推理能力。

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 针对具身社交互动中VLM代理的言语与非言语联合欺骗，构建测试环境。发现代理能策略性结合语言和视觉信号进行欺骗，挑战传统检测方法，强调多模态对齐风险，为安全研究提供新场景。

Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement

👍 10

09/01 08:00

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually impro

中文介绍 提出Harness-of-Harness (HoH)框架，使得基于LLM的编码代理能持续提升，实现多日自主软件开发。通过迭代改进自身能力，无需人工干预即可从高层需求生成完整可用软件系统，延长自主开发跨度。

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

👍 10

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 发现思维链忠实性随偏好线索的位置和传递方式而变化。提出测试方法，在工具返回或原始工件中注入隐性偏好，结果表明模型推理可能失真，对CoT监控安全构成挑战。

EM^2Mem: Event-Centric Multimodal Memory for Large Language Models

👍 9

09/01 08:00

Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as isolated fragments. Although searchable, such fragments are not generation-ready: language models must reconstruct cross-mo

中文介绍 提出事件中心多模态记忆EM^2Mem，将长视频检索到的片段组织为生成就绪的事件描述，而非孤立碎片。通过重建跨模态关联，提升长视频问答的连贯性和准确性。

Agents in the Large: Perception-Centered Architecture for Persistent Agents

👍 8

08/31 08:00

Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and decision-making procedures, enabling agents to reason and act in interactive environments. Existing frameworks largely cast these agents as systems for solving user-specified, bounded ta

中文介绍 提出以感知为中心的持久代理架构，强调环境感知的持续在线处理。不同于解决有界任务的常规代理，该架构支持代理在动态环境中长时间运行并累积知识，迈向更通用的自主代理。

Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs

👍 7

09/01 08:00

Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message routing, output formatting, and termination signals, on which the underlying code re

中文介绍 针对多代理LLM系统中提示优化的稳定性问题，提出控制与数据流分离方法。将执行关键协议与内容生成解耦，避免优化过程中破坏系统稳定性，实现安全高效的提示优化。

E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation

👍 6

08/31 08:00

Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns. Their evolving dynamic environments and long-range dependencies require Large Language Models (LLMs) to continually explore, learn from experience, and adapt their policies over thousands of steps. We introduce E-

中文介绍 提出E-Commerce Bench基准，评估LLM代理在数千步上的长期自主商业运营能力。环境动态变化且依赖长程，要求代理不断探索和适应，该基准揭示当前模型的短板，推动长任务代理研究。

InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal

👍 6

07/21 08:00

Generating professional scholarly content, such as peer reviews and rebuttals, requires an intricate synergy between domain reasoning and factual grounding. This work presents a comprehensive framework for the development and evaluation of specialized scholarly agents, InternReviewer and InternAdvoc

中文介绍 针对学术同行评审和反驳场景，提出评审代理InternReviewer和辩驳代理InternAdvocate。构建客观奖励与评估框架，结合领域推理与事实核查，提升代理生成专业内容的可靠性，支持代理强化学习。

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 针对个人照片库中的视觉叙事检索，提出代理式图像组合方法，超越原子视觉匹配。通过组合相关图像形成连贯故事，满足用户对紧凑视觉叙事的复杂搜索意图，提升检索相关性。

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 评论AI需求与资本开支的自我强化效应：2028年AI资本开支预计超过法国预算，前沿实验室收入增长似乎能合理化任何数字，但这种反射性需求是双刃剑，需警惕泡沫风险。

Compilers 2.0: AI as stochastic optimizer

@cdleary · 2.3K 粉丝 · 100.3K 阅 · 533 赞 · 66 转

09/02 04:00

There has been a lot of discussion following the presentation of the Jalapeño MLA kernel at HotChips and subsequent commentary by SemiAnalysis. As OpenAI’s hardware team, we just barely touched on

中文介绍 OpenAI硬件团队回应Jalapeño MLA内核在HotChips的演示及SemiAnalysis的评论，提出将编译器视为AI随机优化器的新视角，讨论编译器2.0时代如何利用AI进行随机优化。

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平台正式上线OpenAI的ChatGPT Mil，作为该部门生成式AI平台上的前沿能力，标志军事AI应用新进展。

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 作者分享经过2000多小时AI编码实践和采访高产人士后总结的智能体工程完整设置，涵盖工作流、工具与经验，为开发者提供高价值参考。

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工程师介绍用Grok Bot自我构建的过程，将其定位为能管理编码智能体并自主学习的高能力工程实习生，展示智能体驱动的开发新范式。

7 Grok Bots for Marketing

@irabukht · 18.4K 粉丝 · 63.3K 阅 · 536 赞 · 28 转

09/02 07:39

18 things to know and 7 paste-in prompts for running ads, SEO and GEO on Grok Bot. Collected from 1,000+ marketers in our community. Most of us use Grok Bot to run marketing work end to end: Weekly

中文介绍 基于1000+营销人员社区经验，提炼18个要点和7个可粘贴提示词，用于在Grok Bot上运行广告、SEO和GEO，覆盖营销工作流的端到端应用。

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平台推出Starshield AI的Grok for Government，进一步扩展政府生成式AI能力，显示军事与商业AI融合趋势。

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 PostHog指出过度上下文工程可能限制智能体性能，随着模型能力增强，原本必需的上下文信息可能成为负担，建议重新审视AGENTS.md。

Introducing agentic video understanding with Gemini

@GoogleAIStudio · 197.2K 粉丝 · 37.4K 阅 · 522 赞 · 48 转

09/02 02:02

Our new agentic feature for video analysis cuts costs by up to 66% and reduces token consumption by up to 88% while boosting accuracy. Today, we’re launching agentic video understanding across our

中文介绍 Google AI Studio推出基于Gemini的智能体视频理解功能，成本降低66%，token消耗减少88%，准确性提升，为视频分析提供高效方案。

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个精选模板，涵盖技能、记忆和官方插件，用户可直接复制使用，便于启发和快速上手。

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 教学帖从拉格朗日视角直观解读流匹配，解释为何某些模型需数百步迭代生成图像，降低理解门槛，适合图生成模型初学者。

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 Qwen推出zg（zvec-grep），本地优先搜索工具，超越关键字匹配，帮助用户和智能体在大量本地文件中高效定位信息，解决信息分散难题。

Proactive cyber defense for governments and enterprises

DeepMind Blog · 09/03 00:24

中文介绍 DeepMind博客发布文章，介绍面向政府和企业的主动网络防御策略，强调通过AI技术提前识别并应对网络威胁。

Introducing Gemini 3.8 Flash and 3.8 Flash Cyber

DeepMind Blog · 09/03 00:18

中文介绍 DeepMind推出Gemini 3.8 Flash及3.8 Flash Cyber模型，后者专注于网络安全应用，旨在提升AI在安全领域的效能。

Facilitating AI integration with simplicity at scale

MIT Tech Review AI · 09/02 22:00

As companies scale, the technology supporting operations can become a liability just as quickly as it becomes an asset. Disconnected systems, site-specific tools, spreadsheets, and manual workarounds can create data silos that make it harder to spot problems early, coordinate responses, and make dec

中文介绍 MIT科技评论文章指出，企业规模化过程中，技术系统可能成为累赘。数据孤岛和手动流程妨碍问题发现，需简化AI集成以促进扩展。

Real-Time Intelligence with IBM Time Series Models on Confluent

Hugging Face Blog · 09/02 21:49

中文介绍 IBM研究院在Hugging Face博客发布，介绍其时间序列模型与Confluent集成，实现实时智能分析，助力企业数据处理。

ATV Big Air Tour turned 3 days of work into 3 hours with ChatGPT

OpenAI News · 09/02 20:00

ATV Big Air Tour uses ChatGPT Work to speed up marketing, merchandising, and more. It even turned merchandise photos into an inventory website in 15 minutes.

中文介绍 OpenAI报道ATV Big Air Tour利用ChatGPT Work将3天工作量缩短至3小时，包括营销和商品管理，甚至15分钟内将商品照片转为库存网站。

[AINews] Claude Fable/Mythos 5.1: new SOTA model, 75% cache price cut but 70% more output tokens

Latent Space · 09/02 15:46

Queue the usual rush of model launches...

中文介绍 Latent Space报道Anthropic发布Claude Fable/Mythos 5.1新模型，缓存价格下调75%，但输出token增加70%，引发模型发布热潮。

Fable 5.1 🧠, World Labs Atlas 🌍, Cognition $47B 💰

TLDR AI · 09/02 08:00

中文介绍 TLDR AI新闻摘要：Fable 5.1发布，World Labs推出Atlas地图，Cognition估值达470亿美元，AI领域动态频繁。

BenchMIRT: What are LLM benchmarks actually measuring?

Hugging Face Blog · 09/02 05:39

中文介绍 艾伦AI研究所发布BenchMIRT，探讨LLM基准测试实际衡量内容，引发对基准有效性的思考。

Introducing agentic video understanding with Gemini

DeepMind Blog · 09/02 01:08

中文介绍 DeepMind推出Gemini的智能体视频理解功能，提升多模态AI在视频分析领域的应用能力。

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介绍Basis、Clay和Exa Labs等公司利用AI代理优化入职、账户管理和开发者集成，展示企业级AI工作流应用案例。

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报道称，Vercel AI SDK等开源项目用代理团队取代社区PR，形成软件工厂模式，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发布Astra模型，它是首个达到预备框架关键网络安全阈值，并具备更强发布保障的模型。

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允许医疗组织将EHR等数据连接至ChatGPT，帮助临床医生安全获取患者背景和研究资料。

Claude Fable 5.1 and Claude Mythos 5.1

Smol AI News · 09/01 13:44

**Anthropic** released **Claude Fable 5.1** and **Claude Mythos 5.1**, which share base weights but differ in safeguards and routing, showing improved coding performance and usability with a **75% cache-read price cut to $0.25/MTok**. Benchmarks highlight strong coding/science results, though Fable

中文介绍 Anthropic发布Claude Fable 5.1和Mythos 5.1，共享基础权重但保护措施不同，编码性能提升，缓存读取价格降75%至0.25美元/MTok。

[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，可快速创建高质量视频，开启新可能性。