2026-09-09

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

👍 130

09/02 08:00

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 提出双层协调反思框架，用博弈论统一多智能体LLM系统的协调、记忆改进与外部验证。将协调机制建模为双层博弈，优化策略以提升任务分解和反思效率。该方法在多智能体协作中改善性能，优于现有系统。

Dr. Claw: An AI Scientist Workspace for Vibe Research

👍 125

08/31 08:00

Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fragments across chat tools, IDEs, terminals, and writing environments, and the decisions that make it auditable are rarely preserved. We present Dr. C

中文介绍 介绍Dr. Claw，一个集成命令行编码代理的AI科学家工作台，解决端到端研究工具碎片化问题。它统一代码、终端与写作环境，并记录研究决策以保证可审计性，支持交互式研究过程。

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

👍 114

09/03 08:00

Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) structure requires slow, sequential token generation. To overcome this bottleneck, we introduce diffusion-augmented LLMs, a new class of models that defines an AR model distribution w

中文介绍 引入扩散增强LLM，结合自回归与离散扩散实现无损加速。通过扩散过程定义AR分布，并行生成token，在保持质量的同时显著减少顺序解码步骤。实验显示生成速度大幅提升且性能不降。

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

👍 81

09/03 08:00

A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse supervision, while dense same-model guidance can reinforce false confidence or overconcentrate learning on a narrow solution mode. We introduce FlowBalance,

中文介绍 方法利用验证器信号指导模型从自身推理经验中改进，通过平衡信赖性与多样性避免过度集中。实验证明在数学推理任务上提升性能，优于基线。为强化学习提供更稳定的自改进机制。

Iris: Climbing to the Search Frontier

👍 54

09/03 08:00

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 提出35B与397B规模的搜索智能体，基于实体图从网络超链接逆向构造多跳任务，结合数据流水线训练。Iris在搜索任务上达到前沿水平，验证了大规模训练与数据构造策略的有效性。

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

👍 46

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重建在长视频上的退化问题，提出多相对位姿查询方法。利用局部锚点避免外推，通过可扩展的位姿图优化减少漂移。在长序列上显著提升重建精度与一致性。

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

👍 38

08/28 08:00

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 提出端到端模型联合生成语音与全身动作，解决对话中语音与动作分离的问题。通过联合训练协调口语和动作，使虚拟形象在对话中自然移动。实现更好的同步与表达力。

ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation

👍 35

09/03 08:00

We present ENEAS, a unified, text-promptable method for instance tracking and semantic discovery. Text-promptable segmentation models, including the latest foundation models such as SAM 3, still suffer from temporal hallucinations, spatial fragmentation, and semantic misclassification: they fail to

中文介绍 NEAS是一种统一文本提示方法，用于实例追踪与语义发现。结合嵌入引导的集成分割，缓解时间幻觉、空间碎片化与误分类。在基准上提升追踪与分割一致性。

The Attention Triangle in Audio-Video Models

👍 30

09/03 08:00

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 研究音频-视频扩散模型中交叉注意导致的语义泄漏。通过探针分析「注意三角形」的三条交叉边，揭示模型在跨模态对齐中的系统性偏差。提出减轻泄漏的方法，改善生成一致性。

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

👍 26

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 针对无程序化验证的长程智能体任务，提出动态评分标准的细粒度信用分配方法。在无结果监督下，依据多准则拆解奖励并动态调整。提高训练效率与最终成功率。

Enoki: Efficient Multi-Level Hallucination Detection

👍 23

09/01 10:21

Ensuring factuality remains a critical challenge for deploying LLMs in high-stakes settings. Existing hallucination detectors usually operate at a single level: claim-level methods provide interpretable factual units, while span-level methods localize unsupported text. Bridging these views is costly

中文介绍 提出多层级幻觉检测方法，连接声明级与跨度级检测。通过跨层级融合减少成本并提升事实性。实验显示在多个基准上准确率提升，定位更精确。

Using Grounded Theory for Agent Behavior Analysis at Scale

👍 19

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 引入扎根理论分析智能体轨迹，处理上千条数据并发现预定义分类器遗漏的模式。通过定性编码系统化挖掘行为模式。在复杂任务中帮助理解智能体策略。

Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization

👍 18

09/04 08:00

Large language models (LLMs) are increasingly used to formulate optimization models from natural-language problem descriptions, yet realistic operations research (OR) requests are often incomplete: missing objectives, constraints, or business rules can change the resulting mathematical program. Exis

中文介绍 解决LLM在自然语言优化建模中的不完备问题，提出动态预规划澄清。在优化前识别缺失的目标、约束或规则并主动询问。提升最终数学模型的准确性和可行性。

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

👍 18

09/04 08:00

Layer dropout (a.k.a. stochastic depth) has been shown to enable faster training, higher accuracy, and robustness to zero-shot layer pruning in both language and vision transformers. However, as models and datasets have scaled, dropout - particularly layer dropout - has largely disappeared from larg

中文介绍 在大型模型中重新引入层稀疏性（如层dropout），以提升训练与推理效率。通过优化稀疏调度保持模型性能。实验显示在规模增大时，层稀疏带来速度与质量双重优势。

Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs

👍 15

09/03 08:00

Long-video language models cannot look at every frame: an hour sampled once per second is 3,600 images, and a system keeps only a small fixed slice of that pool. Which frames survive that slice is usually treated as a preprocessing detail; we test whether it should be. Published selectors make the c

中文介绍 研究长视频多模态LLM中视觉token选择的影响。对比不同选择策略，并分析「选择-压缩-再投资」过程。揭示选择对任务性能的重要性，提出改进的分配方法。

Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs

👍 14

09/04 08:00

Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal decomposition, and deduction. Although these operations are explicitly distinguished in text, little is known about how they are geometrically organized in representation spaces. To th

中文介绍 对LLM推理链进行机制性解释，探究问题表述、目标分解等操作在表示空间的几何组织。通过探测分析揭示不同推理步骤的嵌入结构，提供对CoT内部运作的洞察。

QCell: Recombining and Aligning Cell Queries for Overlapping Instance Segmentation

👍 14

08/29 08:00

Instance segmentation of overlapping cells in microscopy remains challenging due to semi-transparent structures that produce weak boundaries and mixed visual evidence in overlap regions. Existing methods address this through local regions of interest or shape priors but lack global reasoning across

中文介绍 处理显微镜重叠细胞实例分割，提出QCell方法重组并对齐细胞查询。通过全局推理解决弱边界与混合证据问题。在多个数据集上提升分割精度。

MaxKernel: Agentic Kernel Generation for TPUs

👍 12

09/03 08:00

Designing and authoring high-performance custom kernels for accelerators is a complex task that requires deep hardware-level expertise. Large Language Models (LLM) can be leveraged together with real-time compiler feedback to build agentic systems for kernel generation. In this work, we present MaxK

中文介绍 MaxKernel利用LLM与编译器实时反馈为TPU生成高性能定制内核。代理系统迭代优化代码，显著减少人工设计成本。在多种内核上实现加速。

VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement

👍 12

09/02 08:00

Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of indicating the obligation a clip violates or the moment it fails. We present VeriPhy, an auditable physical-verification system in which a text-only planner compiles the prompt int

中文介绍 提出VeriPhy物理验证系统，利用纯文本规划器编译提示为可审计检查项，定位视频中违反物理规则的帧。为世界模型提供细粒度评估与改进方向。

Causal Foundation Models

👍 11

09/02 08:00

Causal inference is the practice of estimating the effect of a treatment or intervention from data. It traditionally requires a bespoke pipeline for every new problem: first proposing a causal mechanism, selecting a compatible estimator, and finally training it. Meanwhile, across diverse settings an

中文介绍 提出因果基础模型，统一不同任务的因果推断流程。通过预训练学习因果机制与估计器，实现跨环境泛化。在多种因果任务上媲美专用方法，减少人工建模成本。

GPT-6 Astra should be Illegal for SEO

@borjafat · 4.9K 粉丝 · 373.2K 阅 · 502 赞 · 42 转

09/07 19:52

If you want more customers from Google and AI search, but: ↳ ChatGPT keeps giving you keyword lists while your existing pages still need work. ↳ You open Search Console, stare at the numbers, and

中文介绍 作者指出 GPT-6 Astra 对 SEO 的影响令人担忧，因其改变了搜索行为，传统关键词优化失效。内容聚焦于适应 AI 搜索的新策略，提醒从业者调整内容优化方向，避免被算法淘汰。

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

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

09/06 18:44

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 作者原本依赖 Claude Code 构建业务，忽略 Codex 更好的建议。现分享如何将现有系统迁移到 Codex 并保留已有成果，提供技术路径和注意事项，适合考虑转换工具链的开发者。

Reducing cost and improving performance with Claude Platform

@ClaudeDevs · 683.4K 粉丝 · 106.4K 阅 · 1.3K 赞 · 70 转

09/09 01:01

Tuning prompt caching, instructions, and effort can reduce Claude's cost without sacrificing application performance. Performance and cost are often viewed as a trade-off: to spend less, you accept

中文介绍 官方教程：通过调整提示缓存、指令和 effort 参数，可降低 Claude 使用成本而不牺牲性能。说明成本与性能未必对立，给出具体优化配置，帮助开发者高效利用 API。

How to Use GPT-6 Astra to Find Profitable Trading Strategies 24/7

@RohOnChain · 68.8K 粉丝 · 102.3K 阅 · 524 赞 · 48 转

09/08 20:39

I will break down exactly how to build an AI agent like hedge funds that finds profitable trading strategies from the markets 24/7 with GPT-6 Astra. Let's get straight to it. Bookmark This - I'm

中文介绍 教程详解如何用 GPT-6 Astra 构建类似对冲基金的 AI 代理，全天候从市场寻找盈利策略。涵盖代理架构、数据源和回测方法，强调需收藏备用，实操性强。

Using Grok Bot: Figma Photomosaics

@mattyp · 60.1K 粉丝 · 82.8K 阅 · 515 赞 · 56 转

09/08 06:03

You may have seen some three-panel mosaics on your timeline. Here's how you can create them with @bot in @figma. Any designer knows how they'd make one, it's just a bit of a pain in the ass. So we

中文介绍 作者演示如何在 Figma 中用 Grok Bot 快速制作三栏照片马赛克，简化手动流程。适合设计师想自动化繁琐拼贴的案例，提供具体操作步骤和效率提升技巧。

Exactly how I edit videos with Astra

@ForwardEditor · 10.0K 粉丝 · 61.4K 阅 · 512 赞 · 36 转

09/08 08:54

This weekend, I watched a movie with my daughter while my computer worked on a video I would have normally spent most of a day editing. The video was a favor for someone in my personal life. I'm a

中文介绍 作者分享用 Astra 智能编辑视频的实战体验：周末陪孩子时，AI 自动完成原本需一天的工作。展示其省时能力，并可能涉及工作流和用法细节，适合视频创作者参考。

The Math Needed for AI Inference Engineering (Complete Roadmap)

@TheVixhal · 23.0K 粉丝 · 59.7K 阅 · 541 赞 · 58 转

09/08 01:07

In this article, I'm going to break down the essential math you need for AI inference engineering. I'll also share the exact roadmap and resources that helped me personally. Let's get straight to it.

中文介绍 作者结合个人经验，梳理 AI 推理工程所需的数学基础，并给出完整学习路线和资源清单。从核心概念到进阶工具，为想入门推理优化的开发者提供系统性指导。

Grok Bot Marketplace is live!

@ericzakariasson · 87.8K 粉丝 · 58.2K 阅 · 522 赞 · 49 转

09/07 19:05

We launched the Grok Bot Marketplace last week on Grok Bot · Bot Marketplace! It's a shelf of teammates other people already built for real jobs. Pick one, import it into your sidebar, and you're

中文介绍 Grok Bot 市场正式上线，提供他人构建的现成“队友”供用户导入侧边栏，直接用于实际工作。强调即拿即用，降低定制门槛，适合寻求快速部署 AI 助手的用户。

AlphaGenome Atlas: A High-Resolution Map of Human DNA Accelerating Biological Discovery

@GoogleAI · 2.5M 粉丝 · 37.4K 阅 · 643 赞 · 90 转

09/08 22:41

Today, we’re introducing AlphaGenome Atlas 🧬 an interactive platform for genomics discovery. In 2025, @GoogleDeepMind released AlphaGenome to help decode the complex language of our DNA — but

中文介绍 谷歌推出 AlphaGenome Atlas，一个用于基因组学发现的高分辨率人类 DNA 交互平台。基于 2025 年发布的 AlphaGenome，旨在加速生物学研究，提供直观的数据探索工具。

How GPT-5.6 Sol helps run quantum computing experiments

OpenAI News · 09/09 01:00

See how an MIT researcher uses GPT-5.6 Sol with Codex to autonomously run quantum computing experiments, analyze results, and calibrate qubits.

中文介绍 OpenAI新闻介绍，麻省理工学院的研究人员利用GPT-5.6 Sol和Codex自主进行量子计算实验，包括分析结果和校准量子比特。

Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic

Hugging Face Blog · 09/08 22:23

中文介绍 Hugging Face博客文章探讨AI安全对齐问题，主张应精确拒绝话题的特定子集，而非整个话题，以提升安全性和可用性。

AlphaGenome Atlas: A predictive map of every possible DNA letter change in the human genome

DeepMind Blog · 09/08 22:00

AlphaGenome Atlas maps the molecular effects of 9 billion single-letter DNA variants across the human genome.

中文介绍 DeepMind发布AlphaGenome Atlas，绘制人类基因组中90亿个单字母DNA变异的分子效应图，助力遗传学研究。

The Work Now Within Reach

OpenAI News · 09/08 21:00

Explore how more capable, affordable AI can expand the work people and businesses can accomplish—and make growth more economical.

中文介绍 OpenAI探讨更强大且经济实惠的AI如何拓展个人和企业可完成的工作，并使经济增长更具效益。

Introducing ChatGPT Images 2.5

OpenAI News · 09/08 19:30

ChatGPT Images 2.5 helps turn your ideas, sketches, and reference photos into more personalized, polished images that better reflect your ideas.

中文介绍 OpenAI推出ChatGPT Images 2.5，可将想法、草图及参考照片转化为更个性化、精美的图像，更好反映用户意图。

This AI entrepreneur is developing agents that can plan ahead for the unexpected

MIT Tech Review AI · 09/08 18:34

Danijar Hafner’s office in San Francisco’s SoMa district sits mostly empty. His brand-new startup is still in stealth mode and doesn’t even have its name on the door. On the day I visit, there’s only one other person there, and little in the way of furniture. But what it lacks in decor, it makes up…

中文介绍 AI创业者Danijar Hafner在旧金山SoMa区创立隐形初创公司，专注于开发能预先规划突发情况的AI代理。

On the Navier–Stokes Millennium Prize Problem

OpenAI News · 09/08 18:00

We’re sharing an AI-generated solution to the Navier–Stokes Millennium Prize Problem, including a writeup and a formal proof in Lean.

中文介绍 OpenAI发布AI生成的纳维-斯托克斯千禧年大奖问题解决方案，包括报告及Lean形式的正式证明。

Funding grants for new research into AI and teen development

OpenAI News · 09/08 17:00

Apply now for OpenAI’s $5 million grant program supporting independent research on how generative AI affects teen development, well-being, and safety.

中文介绍 OpenAI推出500万美元资助计划，支持关于生成式AI对青少年发展、福祉及安全影响的独立研究。

OpenAI expands initiatives to support journalism from classrooms to newsrooms

OpenAI News · 09/08 08:00

OpenAI is expanding support for journalism with tools, training, and partnerships for students, educators, journalists, and news organizations.

中文介绍 OpenAI扩大对新闻业的支持，为学生、教育者、记者和新闻机构提供工具、培训和合作伙伴关系。

1Password increases engineering productivity 21% with Codex

OpenAI News · 09/08 08:00

Engineers at 1Password use Codex to rapidly build new features and internal tools, reaching production-readiness while maintaining rigorous security policies.

中文介绍 1Password工程师使用Codex快速构建新功能和内部工具，在保持严格安全政策的同时，工程生产率提升21%。

OpenAI managed agents 🤖, TPU inference ⚡, Anthropic $517B compute 💰

TLDR AI · 09/08 08:00

中文介绍 TLDR AI新闻汇总：OpenAI推出管理式代理，TPU推理加速，Anthropic投资5170亿美元用于计算（此数字可能存疑，但按原文）。

The Frontier AEO Tracker: What Astra Chooses (and every other frontier model, and what you can do about it)

Latent Space · 09/08 05:32

Our first Astra project dives into AEO trends, a top asked topic from founders and DX leaders we talk to.

中文介绍 Latent Space推出AEO追踪器，关注前沿模型（如Astra）的选择趋势，为创始人及开发者体验领导者提供洞察。

Supporting independent journalism in Ukraine

OpenAI News · 09/07 08:00

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联合启动AI项目，帮助乌克兰新闻机构增强创新、韧性和独立新闻能力。

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

TLDR AI · 09/07 08:00

中文介绍 TLDR AI新闻：Claude证明费马大定理，自动化AI研究者出现，以及Z1能效芯片的发布。

An Alien Mind

OpenAI News · 09/06 17:00

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 OpenAI的Jakub Pachocki反思日益强大的AI及其对齐挑战，呼吁加强安全防护和国际协调。