2026-07-05

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

👍 44

07/02 08:00

Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see. The simplest contract appends past observations, tool calls, and reflections to every prompt, which makes prior context easy to access but also turns it into a jumbled mixture in which the effect of

中文介绍 提出AgenticSTS，一个有界记忆测试床，用于评估长期LLM agent在有限记忆下的决策能力。通过设计记忆契约限制历史信息访问，避免上下文混杂，提升agent在长周期任务中的表现。

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

👍 41

07/02 08:00

Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it with open-ended software-engineering progress. We introduce Autonomous Policy Evolution, a controlled evaluation setting

中文介绍 提出EvoPolicyGym，一个评估自主策略演化的交互环境。通过受控设定分离策略改进与软件工程进度，量化agent从反馈中持续优化策略的能力，避免最终分数混淆。

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

👍 38

06/26 08:00

We introduce PerceptionRubrics, a rubric-based evaluation framework that addresses the gap between saturated benchmark scores and real-world brittleness. Shifting evaluation from holistic semantic matching to rigorous atomic auditing, PerceptionRubrics pairs 1,038 information-dense images with over

中文介绍 提出PerceptionRubrics，一种基于评分标准的细粒度多模态评估框架。从整体语义匹配转向原子级审计，使用1038张高信息密度图像与人类感知对齐，揭示模型在真实场景中的脆弱性。

Morphing into Hybrid Attention Models

👍 37

06/29 08:00

Hybrid attention models improve long-context efficiency by retaining only a subset of full-attention layers and replacing the remaining layers with linear attention. However, the effectiveness of Transformer-to-hybrid conversion critically depends on which layers preserve full attention. Existing hy

中文介绍 研究如何将Transformer转换为混合注意力模型（部分全注意+线性注意）。提出基于层重要性的选择策略，保留关键层全注意力以最大化长上下文效率，优于现有混合方法。

AgenticDataBench: A Comprehensive Benchmark for Data Agents

👍 25

07/02 08:00

Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amounts of data generated in modern society. Automating this process is essential to reducing labor-intensive efforts for data scientists and enabling scalable data-driven applications. Re

中文介绍 提出AgenticDataBench，一个针对自动化数据科学agent的综合基准。覆盖数据清洗、分析、可视化等任务，评估agent在真实异构数据上的自主能力，推动数据驱动应用的可扩展性。

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving

👍 24

07/01 08:00

In prefill-decode (PD) disaggregated LLM serving, each request is assigned to a decode worker after prefill. Existing decode routers balance only load; for mixture-of-experts (MoE) models this is incomplete: equally loaded workers can differ in latency, since each decode step loads the weights of ev

中文介绍 提出ELDR，一种专家局部性感知的解码路由方法，用于预填充-解码分离的MoE服务。通过考虑每个专家的权重加载局部性，在负载均衡基础上最小化解码延迟，提升MoE模型的服务吞吐量。

Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity

👍 23

06/30 08:00

We present Seed2.0, a model series that takes a meaningful step toward solving complex, real-world tasks. Our approach begins with identifying users' genuine needs and constructing a reliable, forward-looking evaluation system by selecting and abstracting benchmarks grounded in these needs and in re

中文介绍 发布Seed2.0模型系列，面向解决复杂真实世界任务。通过识别用户真实需求并构建前瞻性评估基准，提升模型在开放场景中的鲁棒性与泛化能力。

Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning

👍 22

07/01 08:00

Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens which can lose perceptual nuance. A promising alternative is continuous latent reasoning, where the goal is to discover implicit reasoning pathways tha

中文介绍 提出非对称互变分学习方法，实现多模态连续潜在推理。通过变分推断在连续空间中发现跨模态推理路径，避免离散token丢失感知细节，提升复杂视觉推理任务的精度。

MemSyco-Bench: Benchmarking Sycophancy in Agent Memory

👍 22

07/01 08:00

Memory has emerged as a cornerstone of modern LLM-based agents, supporting their evolution from single-turn assistants to long-term collaborators. However, memory is not always beneficial: retrieved memories often induce a critical issue of sycophancy, causing agents to over-align with the user at t

中文介绍 提出MemSyco-Bench基准，评估LLM agent记忆系统引发的讨好人（sycophancy）现象。设计刻意记忆检索场景，量化agent因记忆偏差而过度迎合用户的程度，为安全记忆设计提供测试。

WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory

👍 20

07/02 08:00

We present WorldDirector, a highly controllable video world model framework designed for persistent dynamic object memory and unrestricted viewpoint exploration. Unlike existing world models that entangle physical dynamics with pixel rendering and rely on continuous visual observation to sustain mot

中文介绍 提出WorldDirector，一种可控制的视频世界模型框架。通过持久动态对象记忆解耦物理动力学与像素渲染，支持自由视角探索，在不依赖连续视觉输入的情况下维持运动一致性。

ASPIRE: Agentic /Skills Discovery for Robotics

👍 18

06/30 08:00

Traditional robot programming is challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse configurations and execution failures. We introduce ASPIRE (Agentic Skill Programming through Iterative Robot Exploration), a continual learning sys

中文介绍 提出ASPIRE（Agentic Skill Programming through Iterative Robot Exploration），一种机器人持续学习系统。通过自主探索发现可复用的技能，结合多模态感知与执行反馈，减少手动编程负担，提升机器人在复杂操作任务中的适应性。

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

👍 17

06/30 08:00

Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-centric, relying on final answer correctness or sequence-level preferences. This suffers from sparse credit assignment, making it difficult

中文介绍 提出步骤感知强化学习方法，用于医学多模态推理。通过细粒度奖励拆解中间推理步骤，打破错误级联，改进稀疏信用分配，提升临床图像诊断的准确性和可解释性。

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads

👍 14

07/01 08:00

In long-context use, large language models frequently synthesize answers from the meaning of a relevant context span rather than literally copy-pasting them. Identifying which attention heads perform this synthesis matters for interpreting long-context model behavior. Yet existing detectors miss the

中文介绍 提出Logit-Contribution Scoring方法，识别LLM中执行非字面检索的注意力头。通过计算注意力头对最终logit的贡献，检测那些从上下文语义合成信息的头，提升长上下文行为解释性。

SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

👍 14

07/02 08:00

Skills are becoming a reusable operational layer for LLM agents, encoding SOPs, domain rules, tool workflows, scripts, and validation routines. In realistic skill repositories, overlapping skills make reliable skill-use difficult. Final verifier success is too coarse for both evaluation and training

中文介绍 提出SkillCoach，通过自进化评分标准评估和提升LLM agent的技能使用能力。针对重叠技能库，设计细粒度rubric引导agent选择、组合和调用技能，超越简单最终验证器的粗糙反馈。

AutoMem: Automated Learning of Memory as a Cognitive Skill

👍 12

07/01 08:00

Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capacity known in cognitive science as metamemory. We bring this perspective to LLMs by treating memory management as a trainable skill. We promote file-system operations to first-class me

中文介绍 提出AutoMem，将记忆管理作为可训练技能（元记忆）学习。提升文件系统操作为一等动作，让LLM agent自主决定编码、检索与组织知识，实现自适应的长期记忆策略。

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination

👍 9

07/01 08:00

Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning. Standard large language models often produce fluent but weakly traceable responses to open-ended materials design problems, making it difficult to det

中文介绍 提出图原生强化学习方法，通过概念重组生成可溯源的科学假设。将材料设计知识表示为图，基于RL探索组合路径，每一步可还原推理过程，提升假设的可解释性和有效性。

InstanceControl: Controllable Complex Image Generation without Instance Labeling

👍 8

06/30 08:00

Controllable image generation methods, such as ControlNet, have demonstrated a remarkable capacity to introduce visual conditions(e.g., depth maps) to guide image generation. However, these methods often struggle with complex multi-instance scenes, frequently leading to attribute confusion among ins

中文介绍 提出InstanceControl，无需实例标注的可控图像生成方法。通过设计条件引导机制，在复杂多实例场景中分离各对象的属性（如颜色、位置），避免属性混淆，提升生成质量。

When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search

👍 8

06/26 08:00

Search agents powered by large language models (LLMs) are increasingly used to solve complex information-seeking tasks, requiring multi-step retrieval and reasoning to fulfill user goals. However, existing benchmarks often assume that user queries are complete and explicit, overlooking the fact that

中文介绍 提出DiscoBench基准，评估LLM搜索代理的主动澄清能力。设计用户查询不完整、模糊的场景，测试代理何时应提问以获取必要信息，从而提升深度搜索的准确性和用户满意度。

The State-Prediction Separation Hypothesis

👍 8

07/01 08:00

Transformers use the same forward computation stream to both predict the next token and store useful state for future token predictions. We formulate the state-prediction separation hypothesis: disentangling the two roles yields better language modeling performance. We design a Transformer variant t

中文介绍 提出状态-预测分离假说：将Transformer中预测下一token和存储状态的功能解耦可提升语言建模性能。设计解耦变体，分别优化预测头与状态存储，实验验证分离带来的困惑度下降。

AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models

👍 7

07/02 08:00

Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG). However, current evaluation protocols are largely confined to zero-shot assessments on general, daily-life benchmarks. This creates a critical disconnect from real-world applications in special

中文介绍 提出AnyGroundBench，一个专门领域视频定位基准。覆盖工业、医疗等专业场景，评估VLM在非日常环境中的时空定位能力，揭示日常基准与真实应用之间的差距。

Career advice in the age of AI

@philhchen · 9.1K 粉丝 · 179.1K 阅 · 516 赞 · 34 转

07/03 05:25

AI models get better at anything you can write a loss function for, and school is mostly loss functions: well-defined problems graded against known answers. Therefore, the valuable work of the next

中文介绍 AI擅长有明确损失函数的问题，学校教育也类似。未来最有价值的工作是提出“好问题”而非解已知题，强调创造力与模糊定义问题的能力。

Your AI, your growth

@arthurmensch · 74.0K 粉丝 · 162.7K 阅 · 539 赞 · 76 转

07/04 05:31

Of course you need to use open-source models if you’re an enterprise leader. Close model providers, that are now forcing data retention, are gaining immense leverage on your business if you don’t. As

中文介绍 企业领导者必须使用开源模型。闭源模型提供商正通过强制数据保留对业务施加巨大杠杆，建议采用开源以避免被锁定。

How to build a second brain with Fable 5

@EXM7777 · 121.1K 粉丝 · 83.6K 阅 · 518 赞 · 48 转

07/03 22:06

I'm going to show you, step by step, how to turn Fable 5 into a machine that knows your business inside out... and ships outputs that look nothing like what everyone else is getting the tool is a

中文介绍 逐步教学如何用Fable 5打造第二大脑：让工具深度了解业务，输出个性化成果，而非千篇一律的通用结果。

THE MOST VALUABLE THING YOU CAN DO WITH FABLE 5 IN THE NEXT 24 HOURS

@AlexFinn · 459.5K 粉丝 · 72.5K 阅 · 565 赞 · 34 转

07/03 08:20

If the first thing you did with Fable 5 was vibe code, you're using it wrong. Fable 5 isn't a vibe coding tool. It's an operating systems tool. Let me explain. Fable 5 is the first model I've ever

中文介绍 Fable 5并非viibe coding工具，而是操作系统工具。首次使用时若直接用于编程就错了，应将其视为系统级编排者。

Agentic Autonomy Levels

@addyosmani · 404.9K 粉丝 · 53.5K 阅 · 525 赞 · 66 转

07/03 11:29

In most conversations about agentic engineering, the action has changed from prompting to operating. Here's a frontier looking into the fog: software factories, goals, loops, background sessions,

中文介绍 探讨AI agent的自主性层级：从提示工程转向操作工程，提出“软件工厂”概念，涉及目标循环、后台会话等前沿方向。

A Field Guide to Fable: Finding Your Unknowns

@trq212 · 299.3K 粉丝 · 40.1K 阅 · 534 赞 · 43 转

07/04 01:43

Working with Claude Fable 5 keeps re-teaching me an old lesson: the map is not the territory. The map, a representation of the work to be done, is my prompts and skills and context, it’s what I give

中文介绍 与Claude Fable 5协作的经验：提示和技能是“地图”而非“领土”，需警惕将抽象方案误当作真实工作，强调持续探索未知。

Fable is back, here's how I use it in Cursor

@ericzakariasson · 76.4K 粉丝 · 37.9K 阅 · 567 赞 · 24 转

07/02 19:10

Fable is back in Cursor, and here's a pattern I've been exploring and some other ways I've been getting the most out of the model. Fable as orchestrator, Composer as workers It's easy to put

中文介绍 Fable回归Cursor后的使用模式：将Fable作为编排器，Composer作为执行工人，分工协作以提高开发效率。

Your One-Page PyTorch Training Pipeline Cheat Sheet.

@0xkozue · 690 粉丝 · 24.9K 阅 · 501 赞 · 46 转

07/02 17:03

The entire engine of Deep Learning works by making tiny, continuous adjustments to a model's weights. This is my PyTorch training pipeline cheat sheet. If you spot any mistakes or have suggestions for

中文介绍 发布一页PyTorch训练流程备忘单，涵盖模型权重微调的整个流程，适合深度学习实践者快速参考。

Google DeepMind and A24 announce first-of-its-kind research partnership

DeepMind Blog · 07/03 22:25

中文介绍 Google DeepMind与电影公司A24宣布建立首创研究合作伙伴关系，具体内容未披露，涉及AI与影视结合的可能性。

AIEWF Daily Dispatch: The great loops debate and the state of AI engineering

Latent Space · 07/03 13:11

The AI Engineer World’s Fair ended with a debate about loops, a report on the state of AI engineering, and closing keynotes focused on what to build next.

中文介绍 AI工程师世界博览会（AIEWF）闭幕，围绕循环（loops）展开辩论，发布AI工程现状报告，闭幕演讲聚焦下一步建设方向。

Vercel's Andrew Qu on why agents are a new kind of software

Latent Space · 07/03 08:08

The Vercel Chief of Software explains how its agent framework, eve, was created — and why skills, sandboxes and agent-readable websites now matter.

中文介绍 Vercel首席软件官Andrew Qu阐述其智能体框架eve的创建过程，强调技能、沙箱和智能体可读网站的重要性。

Meta Watermelon 🍉, Anthropic Samsung chips 🤝, autoresearch in practice 📈

TLDR AI · 07/03 08:00

中文介绍 Meta推出“西瓜”项目，Anthropic与三星芯片合作，自动研究（autoresearch）投入实践，具体细节未披露。

The website of the future may assemble itself for every visitor

Latent Space · 07/03 05:25

Adobe is experimenting with “agentic sites” that generate pages around an individual user’s intent. At AIEWF, we talked to Carlos Sanchez about the Web's future.

中文介绍 Adobe正在试验“智能体网站”，根据用户意图动态生成页面；在AIEWF上与Carlos Sanchez探讨Web未来。

Achieving operational excellence with AI

MIT Tech Review AI · 07/02 23:37

Frameworks like Lean Six Sigma and business process management (BPM) first gained traction because they promised clarity in the chaos—a structured way to bring order to messy, sprawling operations. Lean Six Sigma emphasized statistical rigor and quality control; BPM created end-to-end maps of how wo

中文介绍 文章探讨利用AI实现运营卓越。Lean Six Sigma和BPM等框架曾通过结构化方式整顿混乱运营，Lean Six Sigma强调统计严谨与质量控制，BPM侧重端到端流程管理。

Skill engineering and the case against one-shot AI design

Latent Space · 07/02 22:36

Paul Bakaus talks to us about Impeccable, human judgment in a 'loopmaxxing' era, and why agents still need people to steer them.

中文介绍 Paul Bakaus讨论技能工程与“一次成型”AI设计的反对观点，强调在“循环最大化”时代仍需人类判断引导智能体。

Teaching AI to run with the turbines

MIT Tech Review AI · 07/02 20:51

Artificial intelligence may have captured the public imagination through chatbots and image generators, but some of its most consequential use cases are unfolding far from consumer-facing tools. In industries where physical infrastructure, operational continuity, and safety are paramount, AI is beco

中文介绍 AI最深远的影响出现在远离消费者工具的领域，如物理基础设施、运营连续性和安全。文章探讨AI在涡轮机等工业场景中的应用。

[AINews] not much happened today

Latent Space · 07/02 15:10

another quiet day.

中文介绍 当天无重大AI新闻发生，市场平静。

AIEWF Daily Dispatch: Autoresearch and the tension between AI and human agency

Latent Space · 07/02 14:13

The software factory vision met resistance today from speakers defending human understanding and control.

中文介绍 AIEWF日报：自动研究（autoresearch）引发AI与人类能动性之间的张力，多位演讲者捍卫人类理解与控制，对软件工厂愿景提出质疑。

not much happened today

Smol AI News · 07/02 13:44

**Fullstack Code Arena** extends coding agent evaluation to include **databases, API keys, deployments, and structured tool use**, marking a shift to end-to-end app shipping. **LangChain** released **LangSmith** with unified tracing and **OpenWiki** for auto-generated docs, while **LlamaIndex** demo

中文介绍 Fullstack Code Arena扩展编码智能体评估至数据库、API密钥、部署等，转向端到端应用交付。LangChain发布LangSmith统一追踪和OpenWiki自动生成文档。

Gemini Flash upgrade ⚡️, Meta AI cloud 🌐, ZCode 👨‍💻

TLDR AI · 07/02 08:00

中文介绍 Gemini Flash升级，Meta推出AI云服务，ZCode发布，具体细节未披露。

Autoresearch: The feedback loop behind self-improving agents

Latent Space · 07/02 07:52

Introspection co-founder Roland Gavrilescu explains autoresearch, agent “recipes,” self-improving loops, and why humans remain central to the software factory.

中文介绍 Introspection联合创始人Roland Gavrilescu阐述自动研究（autoresearch）、智能体“配方”、自我改进循环，强调人类在软件工厂中的核心地位。

How Cursor deploys AI inside the enterprise

Latent Space · 07/02 03:03

Cursor's Pauline Brunet explains how her team of Forward Deployed Engineers help organizations implement agents — essentially setting up software factories.

中文介绍 Cursor的Pauline Brunet介绍其前部署工程师团队如何帮助组织部署智能体，实质是构建软件工厂。

🔬 The Coolest Diffusion Research Isn't in LLMs — Evan Feinberg & Sergey Edunov, Genesis Molecular AI

Latent Space · 07/01 22:42

Why the Llama lead left Meta for drug discovery, PEARL's zero-shot OpenBind win, and what becomes possible when co-folding finally crosses the accuracy threshold.

中文介绍 Genesis Molecular AI的Evan Feinberg和Sergey Edunov探讨扩散研究在药物发现中的应用，包括Llama负责人离开Meta加入该领域、PEARL在OpenBind上的零样本胜利，以及共折叠精度突破带来的可能性。