2026-07-26

AREX: Towards a Recursively Self-Improving Agent for Deep Research

👍 127

07/23 08:00

Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed into tractable constraint-wise checks. This discovery--verification asymmetry suggests that a research agent should do mo

中文介绍 提出AREX，一种递归自我改进的深度研究代理。利用发现-验证不对称性，代理在搜索过程中不断生成验证约束的候选方案，并通过递归自我改进提升搜索效率，无需人工干预。

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

👍 56

07/22 08:00

Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlapped communication overhead, and inefficient kernel execution. While most large-scale LLM training syst

中文介绍 针对万亿参数MoE模型的全参数后训练，提出SLAI T-Rex系统。在Ascend SuperPOD上解决内存压力、通信重叠和内核执行效率问题，实现高效分布式训练。

K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs

👍 55

07/23 08:00

Large language models are increasingly used in K-12 education, but existing benchmarks mainly test exam question answering rather than understanding how curriculum knowledge is structured and visually presented. We call this capability curriculum cognition. It covers prerequisite chains, concept tax

中文介绍 构建K12-KGraph课程对齐知识图谱，用于评估和训练教育大模型。包含先修链、概念分类等结构，提升模型对课程知识的认知能力，超越传统考试问答评测。

ReferTrack: Referring Then Tracking for Embodied Visual Tracking

👍 49

07/22 08:00

Embodied visual tracking (EVT) requires a mobile agent to continuously follow a specific target described in natural language using only onboard vision. While recent vision-language-action (VLA) policies unify target identification and trajectory planning, their chain-of-thought (CoT) reasoning ofte

中文介绍 提出ReferTrack框架，用于具身视觉追踪。先通过语言描述定位目标，再执行跟踪，避免VLA策略中CoT推理的冗余路径规划，提升追踪准确性和效率。

Visual Contrastive Self-Distillation

👍 41

07/23 08:00

On-policy self-distillation (OPSD) is promising as it removes the external teacher required by on-policy distillation (OPD), yet it still needs asymmetric information between teacher and student to ensure that the self-teacher provides a stronger learning signal than the student. Existing methods cr

中文介绍 提出视觉对比自蒸馏方法，解决在线自蒸馏中师生信息不对称问题。通过对比学习构建更强的自教师信号，无需外部教师，在多个视觉任务上提升学生模型性能。

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text

👍 35

07/23 08:00

Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world. Many spatial tasks are grounded in continuous visual scenes, where locations, regions, and paths are more naturally expressed by pointing, marking, or drawing than by r

中文介绍 提出用生成像素而非文本评估空间认知。通过让模型在视觉场景中标注、画框等方式表达位置和路径，更自然地评估多模态大模型的空间智能，避免LLM文本描述的局限性。

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

👍 28

07/22 08:00

As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evaluation systems remain confined to scoring documents independently and aggregating via nDCG, ignoring inter-document intera

中文介绍 提出基于评分准则的文档集合选择与排序方法，超越传统相关性排序。考虑文档间交互，为LLM生成提供更优的文档集，提升下游任务生成质量。

An Exam for Active Observers

👍 24

07/17 08:00

Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued that this active observation is essential for a wide range of tasks. Whether today's multimodal large language models (M

中文介绍 设计主动观察者考试，测试多模态大模型在闭环视觉中的表现。通过逐步重定向注视的任务，发现模型在主动观察方面与人类存在显著差距，为未来研究提供基准。

NVIDIA-labs OO Agents: Native Python Object-Oriented Agents

👍 22

07/22 08:00

Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We present NVIDIA Object-Oriented Agents (NOOA), a model-agnostic Python framework for building reliable AI agents. NOOA takes a simpler approach: an agent is a Python object. Its method

中文介绍 提出NVIDIA Object-Oriented Agents（NOOA），一种Python原生面向对象代理框架。将代理定义为Python对象，方法对应工具，消除模板和回调代码，简化开发流程。

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

👍 20

07/23 08:00

We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard. At its core is a unified evaluation framework for constructing and running distribution-informed coding-agent

中文介绍 发布Tencent WorkBuddy Bench，多领域编码代理评测基准。采用抗污染任务构造方法，提供统一评估框架和跨模型排行榜，衡量编码代理实际能力。

Color Pass-Through via Camera-Display Coupling

👍 18

07/14 08:00

When a real-world scene is captured by a smartphone camera and viewed on its screen, the displayed image often differs noticeably from the original scene in color, brightness, and contrast. This gap persists despite substantial advances in both modern cameras and displays. A key reason is that most

中文介绍 提出相机-显示器耦合的颜色透传方法，缩小真实场景与屏幕显示之间的颜色差异。通过联合优化相机和显示器的色彩处理管线，提升色彩、亮度和对比度的还原精度。

LLMs Get Lost in Evolving User Intent

👍 18

07/22 08:00

As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction. Yet genuine interaction is inherently dynamic: users rarely specify their intent upfront, instead disclosing, revising, and reshaping it as the conversat

中文介绍 发现LLM在协作对话中难以跟踪用户不断演变的意图。通过构建动态意图数据集，揭示模型在用户逐步披露和修正需求时的表现下降，呼吁改进交互式对齐方法。

Self-Supervised Learning of Structured Dynamics from Videos

👍 16

07/23 08:00

Understanding motion in video is a fundamental challenge for visual learning, as frame-to-frame change entangles two sources of dynamics: camera motion and object motion. This decomposition has remained underexplored in representation learning, partly because these factors are tightly coupled in nat

中文介绍 提出自监督学习结构化动态的方法，从视频中解耦相机运动与物体运动。无需标注，仅利用帧间变换学习分离表示，在运动理解任务上优于现有方法。

Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models

👍 14

07/21 08:00

Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solution to large-scale knowledge injection. Although hypernetworks are typically applied for test-time adaptation, we explore their use in train-time know

中文介绍 研究超网络用于大模型知识注入的缩放规律。探索在训练阶段用超网络注入事实知识，发现其性能随模型规模呈幂律增长，为可靠注入知识提供理论指导。

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

👍 12

07/11 08:00

Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily heuristic and fail to identify the essential cause of PPO-Clip's failure. This

中文介绍 揭示PPO-Clip在LLM强化学习中导致探索崩溃的本质原因，提出黎曼流形等距策略优化（RIPO）。通过流形上的等距约束避免策略坍缩，提升推理能力。

Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers

👍 11

07/23 08:00

Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evolve across views. Existing autoregressive video diffusion pipelines carry forward observation history as conditioning context, which makes shared st

中文介绍 提出流式多智能体自回归扩散模型，引入世界状态寄存器。维护跨智能体和视角的持久化世界状态，实现一致的多智能体交互世界生成。

Sample-Efficient Learning from Agent Experience

👍 9

07/23 08:00

Real-world agent learning is often constrained by costly environment interactions, such as running time-consuming experiments or obtaining human feedback. In-context learning offers a highly sample-efficient way for agents to learn from their own interaction histories, but its gains disappear once t

中文介绍 提出从代理经验中样本高效学习方法。利用上下文学习从自身交互历史中学习，但面临长历史离线学习的挑战。通过重放机制保留关键经验，提升样本效率。

AutoIndex: Learning Representation Programs for Retrieval

👍 9

07/21 08:00

We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over program

中文介绍 提出AutoIndex框架，学习表示程序（可执行变换）将原始文档映射为检索系统的表示。通过程序搜索而非调参，自动发现最优文档变换，提升检索效果。

Multi-Turn On-Policy Distillation with Prefix Replay

👍 8

07/16 08:00

We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn interaction histories. Fully online OPD is costly because each update requires fresh student rollouts through the envir

中文介绍 研究多轮在线蒸馏（OPD）用于智能体任务，提出前缀重放机制。复用历史交互前缀，减少全在线rollout成本，同时保持师生对齐效果，提升训练效率。

Robostral Navigate

👍 8

07/22 08:00

Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently. Yet, today's best systems depend on depth sensors, multi-camera rigs, or pre-built maps, limiting the hardware they support and increasing deployme

中文介绍 提出Robostral Navigate，一种轻量级导航系统。无需深度传感器或预建地图，仅靠单目视觉和低成本硬件，跨机器人本体高效训练，实现通用导航部署。

The complete Graph Engineering playbook for Claude Code

@Gyome1_ · 3.9K 粉丝 · 220.0K 阅 · 504 赞 · 65 转

07/23 16:53

Most people are still using Claude Code like a very expensive intern. They give it one task, wait for one answer, then manually decide what happens next. But the teams getting the most leverage from

中文介绍 Gyome1_ 分享 Claude Code 完整图工程手册，指出多数人将其当作昂贵实习生——单任务单回答后手动决策，而高效团队利用图结构获得更大杠杆，并给出系统化工作流方法。

Frontier Diffusion & Control

@satyanadella · 7.5M 粉丝 · 153.7K 阅 · 923 赞 · 114 转

07/24 00:31

In a world where software has real marginal cost for the first time, how do we ensure frontier benefits are diffused across the entire ecosystem? The key is to optimize the cost-to-outcome frontier in

中文介绍 Satya Nadella 探讨前沿 AI 的扩散与控制。指出软件首次具有真实边际成本，关键在于优化「成本-结果前沿」以确保前沿利益惠及整个生态系统。

this system will change your life...

@eptwts · 116.8K 粉丝 · 140.0K 阅 · 514 赞 · 28 转

07/24 01:21

the consensus on self-hosted agents is that they're simply coding tools... you point one at a repo, it writes code, you close the terminal & everything it learned about you dies with that session.

中文介绍 eptwts 批评自托管 agents 被误认为仅是编码工具，会话结束后所学即失。暗示需要系统化改造实现持续学习，否则浪费 Agent 潜力。

Trajectory: A Standard Format for Agent Experience Data

@Letta_AI · 9.8K 粉丝 · 86.5K 阅 · 504 赞 · 31 转

07/24 14:07

Introducing trajectory, an open-source package that normalizes coding-agent sessions from @AnthropicAI Claude Code, @OpenAI Codex, @pidotdev, @LangChain deepagents, @openclaw, Letta Code, and other

中文介绍 Letta_AI 发布开源包「trajectory」，标准化来自 Claude Code、OpenAI Codex、LangChain deepagents 等多个编码 Agent 的会话数据格式，便于跨平台分析和复现。

Why Software Factories Fail

@dexhorthy · 23.8K 粉丝 · 64.9K 阅 · 515 赞 · 50 转

07/25 00:51

or: the harness is not enough Update - the talk version of this post is live on youtube: https://www.youtube.com/watch?v=Ib5GBkD555M i guess we doin loops now We're all racing to put AI coding into production. A lot has

中文介绍 dexhorthy 分析「软件工厂」为何失败：仅靠工具链（harness）不足。将 AI 编码投入生产需要更全面的循环方法，视频版已发布在 YouTube。

The new rules of context engineering for Claude 5 models

@trq212 · 318.0K 粉丝 · 48.6K 阅 · 1.2K 赞 · 119 转

07/25 01:45

I’ve written previously about how to best prompt the newest generation of Claude 5 models and work with them iteratively to discover what you want to build. But when you send a message to Claude, the

中文介绍 trq212 分享 Claude 5 模型上下文工程新规则。在迭代 prompt 基础上，进一步探讨消息发送后的上下文管理技巧，帮助更高效地引导模型输出。

Practical multi-agent orchestration in Codex

@pvncher · 30.4K 粉丝 · 44.0K 阅 · 565 赞 · 33 转

07/25 01:30

GPT-5.6 Sol gets especially interesting when it has a team to work with. Codex's new Multi-Agent V2 tools give Sol and Terra a natural way to delegate tasks, share updates, and coordinate through

中文介绍 pvncher 展示 Codex 多智能体编排实践。GPT-5.6 Sol 在团队协作时效果更佳，Codex 新 Multi-Agent V2 工具支持自然任务委派和状态同步。

I Can Finally Talk to ChatGPT the Way I Actually Think

@derrickcchoi · 9.1K 粉丝 · 40.1K 阅 · 516 赞 · 31 转

07/24 04:08

This must be a little like how Tony Stark feels talking to Jarvis. I'm really excited that we just launched ChatGPT Voice across Work and Codex in the ChatGPT desktop app. I don't know about you but

中文介绍 derrickcchoi 宣布 ChatGPT Voice 已登陆 Work 和 Codex 桌面应用。用户可像钢铁侠与贾维斯对话一样，以自然语音与 ChatGPT 交流，体验直观。

How we teach AI models

@leerob · 272.8K 粉丝 · 32.9K 阅 · 550 赞 · 51 转

07/24 09:39

How do AI models learn new skills and behaviors? The process is surprisingly human and easy to understand, even if you don’t have a machine learning background. Helpful colleagues AI models,

中文介绍 leerob 解析 AI 模型学习新技能和行为的过程，类比人类学习方式。强调即使没有 ML 背景也能理解，模型如同「乐于助人的同事」，易于上手。

Building the Next Layer of the Agent Economy on BNB Chain

@OptimaiNetwork · 99.3K 粉丝 · 6.1K 阅 · 509 赞 · 112 转

07/23 23:10

Over the past year, AI has moved beyond chat interfaces toward autonomous systems capable of reasoning, planning, and taking action. The next challenge is no longer building more capable agents - it

中文介绍 OptimaiNetwork 探讨在 BNB Chain 上构建 Agent 经济下一层。AI 已从聊天转向自主系统，下一挑战不再是增强能力，而是建立协调与交易层。

[AINews] Claude Opus 5: Fable-level performance at Opus price (half Fable)

Latent Space · 07/25 15:25

ain't nobody beats Anthropic at distilling Fable!

中文介绍 Anthropic推出Claude Opus 5模型，声称性能媲美Fable，但价格仅为后者一半，凸显其蒸馏技术优势。

Opus 5

Smol AI News · 07/24 13:44

**Anthropic** launched the **Claude Opus 5** model, which sparked mixed reactions including benchmark scrutiny and praise for its coding-agent capabilities. The model achieved an **Epoch Capabilities Index (ECI) of 159**, slightly below **Fable 5's 161**, but matched Fable 5 on software engineering

中文介绍 Anthropic发布Claude Opus 5模型，引发混合反响：基准测试受质疑，但编码代理能力获好评。其Epoch Capabilities Index（ECI）为159，略低于Fable 5的161。

[AINews] Black Forest Labs FLUX 3 - Multimodal Flow Models that beat Seedance 2.0, Gemini Omni and Grok Imagine, and FLUX-mimic video-action robotics model

Latent Space · 07/24 12:30

A HUGE win for BFL!

中文介绍 Black Forest Labs发布FLUX 3多模态流模型，性能超越Seedance 2.0、Gemini Omni及Grok Imagine，并推出FLUX-mimic视频动作机器人模型，被视为重大胜利。

ChatGPT Health 🩺, Fugu-Ultra 1.1 🐡, Runway Media Router 🎬

TLDR AI · 07/24 08:00

中文介绍 OpenAI在ChatGPT中推出健康功能；Fugu-Ultra 1.1模型发布；Runway推出Media Router工具。

How AI helps scientists design the next generation of medicines

MIT Tech Review AI · 07/23 20:00

Designing and developing a new medicine is an expensive, failure-prone scientific challenge. A new drug can take many years to develop, at the cost of a significant investment. And even then, most possible candidates never reach the patient. For biologic medicines, therapies made from engineered pro

中文介绍 AI正在帮助科学家设计下一代药物，传统药物开发成本高、失败率高。文章探讨AI如何加速生物药等新型疗法的研发过程。

not much happened today

Smol AI News · 07/23 13:44

**The Stack v3** is released as the largest open code dataset with **114 TB raw data**, **224M repositories**, and **5T deduplicated tokens**, significantly expanding data for open code models and cyber-defense. The debate on **distillation** continues as a key ideological fault line, with calls for

中文介绍 The Stack v3发布，成为最大开放代码数据集：114TB原始数据、2.24亿代码仓库、5T去重token，为开放代码模型和网络安全防御提供数据支持。关于模型蒸馏的辩论仍在继续。

[AINews] "Laguna S 2.1 Released: Cheaper than Deepseek v4 Flash, Better than V4 Pro"

Latent Space · 07/23 13:18

a quiet day lets us highlight a new neolab win.

中文介绍 Neolab发布Laguna S 2.1模型，宣称成本低于Deepseek v4 Flash，性能优于V4 Pro，被视为新胜利。

Inside the Model Factory — Eiso Kant, Poolside AI

Latent Space · 07/23 13:09

Poolside's co-CEO on how his small team of top researchers built a model factory capable of training Laguna S - a 118B MOE beating Thinky's ~1T open weights model... and this is just the beginning.

中文介绍 Poolside AI联合CEO Eiso Kant透露，其小型团队打造的模型工厂训练出118B参数MOE模型Laguna S，性能超越Thinky约1T参数的开放权重模型，并表示这只是开始。

Launching Health in ChatGPT

OpenAI News · 07/23 08:00

Health in ChatGPT now lets eligible U.S. users securely connect medical records and Apple Health to get more personalized insights and better understand their health.

中文介绍 OpenAI在ChatGPT中推出“健康”功能，允许符合条件的美国用户安全连接医疗记录和Apple Health数据，以获得更个性化的健康洞察。

Bringing Nunchaku 4-bit Diffusion Inference to Diffusers

Hugging Face Blog · 07/23 08:00

中文介绍 Hugging Face将Nunchaku 4-bit扩散推理集成到Diffusers库中，提升模型推理效率。

Cursor Router 🔀, OpenAI Presence 🤖, AMD + Anthropic deal 🤝🏻

TLDR AI · 07/23 08:00

中文介绍 Cursor推出Router功能；OpenAI发布Presence功能；AMD与Anthropic达成合作协议。

Accelerating the frontiers of scientific discovery: Google’s $40M commitment to the Genesis Mission

DeepMind Blog · 07/22 21:38

Google commits $40M in AI tokens and credits for the Genesis Mission

中文介绍 Google向Genesis Mission承诺4000万美元的AI代币和积分，旨在加速科学前沿发现。

Building AI infrastructure with the Effingham County community

OpenAI News · 07/22 21:00

OpenAI announces Project Camellia in Effingham County, Georgia, with commitments to responsible energy, community investment, jobs, and access to Codex.

中文介绍 OpenAI宣布在佐治亚州Effingham County启动“Project Camellia”AI基础设施项目，承诺负责任能源、社区投资、创造就业并开放Codex访问。

How news organizations are using AI to advance their vital missions

OpenAI News · 07/22 21:00

News organizations are using AI to strengthen reporting, grow audiences, and improve business operations, with OpenAI tools supporting journalists and publishers worldwide.

中文介绍 新闻机构正利用AI强化报道、扩大受众及改善业务运营，OpenAI工具为全球记者和出版商提供支持。

Advancing the next era of national science

OpenAI News · 07/22 20:00

OpenAI outlines its commitment to advancing American science working with the U.S. Department of Energy and national labs to use frontier AI to accelerate discovery.

中文介绍 OpenAI阐述其致力于推动美国科学发展的承诺，将与能源部和国家实验室合作，利用前沿AI加速科学发现。