2026-08-23

EnvHarness: Awakening Static Worlds for Agent Learning

👍 246

08/20 08:00

LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While recent environment generation methods attempt to address this, they require domain-specific pipelines, rely on expensive

中文介绍 针对LLM智能体训练中环境静态、无法适应智能体弱点的问题，提出EnvHarness，唤醒静态世界，实现动态环境生成，以自适应提升智能体学习效率。

Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

👍 141

08/17 08:00

Embodied agents are increasingly used to close the gap left by end-to-end policy models. Yet the agentic path has not realized closed-loop learning in physical execution: existing harnesses remain largely open-loop, following fixed skills during rollout and reflecting only after an episode completes

中文介绍 针对具身智能体闭环学习缺失，提出Zetta ζ，一种高效的闭环具身训练框架，支持物理执行中的自我进化，实现真正的闭环学习。

SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation

👍 115

08/19 08:00

Programmable logic controllers (PLCs) run industrial plants, and large language models can already generate independent program organization units (POUs) for them. Whether such logic integrates into an existing PLC project and then runs correctly has been checked only in limited tests. We present Se

中文介绍 针对PLC代码生成中项目级集成与验证不足，提出SemaPLC，一种项目化、验证门控的智能体框架，确保生成的代码在真实项目中正确运行。

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

👍 112

08/19 08:00

Training terminal agents requires scalable executable supervision, yet synthesizing high-quality terminal tasks remains challenging. Each task couples an instruction, an initialized environment, a reference solution, and an executable verifier; if these artifacts are generated from inconsistent assu

中文介绍 针对终端智能体训练中任务合成质量不高，提出FACET，保持源意图和可执行状态，合成高质量终端任务，提升训练效率。

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

👍 91

08/19 08:00

Reinforcement learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-language models, yet its strongest successes still depend heavily on ground-truth supervision (e.g., verifiable reward). Such annotations are costly to obtain and become increasingly scarce

中文介绍 提出Co-RL，利用多智能体强化学习中的多样群体，无需监督信号即可涌现推理能力，降低对可验证奖励的依赖。

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

👍 88

08/13 08:00

Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation. Yet workflow coverage alone does not provide access to the full evidence on which scientific discovery depend

中文介绍 提出OmniScientist，一种全模态全学科的AI科学家，自动化从假设生成到代码执行再到论文撰写的完整科研流程。

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

👍 58

08/20 08:00

Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program behavior but also the evidence underlying scientific conclusions. Yet existing evaluations of coding agents largely emphasize aggregate task succes

中文介绍 评估编码智能体在科学工程任务中的表现，提出SWE-bench Science基准，强调科学代码错误对结论的影响，揭示现有评估的不足。

SPADE: Self-Play in Adaptive Synthetic Executable Environments

👍 47

08/19 08:00

Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, statically synthesized, or frozen-verifier) keep the goal distribution fixed as the learner scales. We introduce SPADE (Self

中文介绍 提出SPADE，通过自适应合成可执行环境中的自我对弈，为语言智能体生成多样化、自适应的训练目标，支持持续自我改进。

Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis

👍 32

08/19 08:00

Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by single-answer evaluation and benchmarking protocols. To address this, we introduce Top-K prompting as a robust training and inference paradigm to bet

中文介绍 针对单步逆合成的一对多问题，提出Top-K提示训练范式，训练化学合理性感知的LLM，改善多解评估和生成质量。

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

👍 31

08/20 08:00

Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions. However, existing memory benchmarks mainly evaluate whether information is correctly extracted, stored, and retrieved, while largely overlooking how retrieved memori

中文介绍 提出MemTrapBench，基准测试LLM记忆使用中的认知陷阱，关注检索信息如何被模型利用，而不仅是提取和存储。

SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback

👍 29

08/13 08:00

Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no closed loop through which they might improve from the interaction failures they actually cause. Recent work does close this loop, but derives its feedback from single-turn question-an

中文介绍 提出SkillEvo，利用多轮交互反馈为智能体技能提供自更新进化梯度，实现技能从失败中持续改进的闭环。

Repo0: Design-Driven Zero-to-All Code Generation

👍 17

08/20 08:00

Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption does not hold in zero-to-all code generation, where an agent must construct an entire software project directly from natural-language

中文介绍 针对从零代码生成中仓库架构未定义的问题，提出Repo0，设计驱动的零到全代码生成，直接根据自然语言需求构建完整软件项目。

The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning

👍 17

08/14 08:00

Popular facts are memorised more deeply during pretraining and resist removal longer than rare ones, yet existing LLM unlearning methods apply uniform gradient pressure regardless of training-data frequency. We propose the AdaPop (Adaptive Popularity) method, which combines local token confidence wi

中文介绍 针对LLM遗忘中流行事实难以移除的问题，提出AdaPop方法，结合局部token置信度与自适应梯度压力，提升遗忘效果。

Looped Language Models Improve Compositional Tool Calling

👍 16

08/17 08:00

Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored. We study this question in compositional tool-calling settings, where models must coordinate multiple API calls, maintain intermediate state, and preserve

中文介绍 探索循环语言模型在组合工具调用中的能力，通过循环结构改进多API调用、状态维护和组合推理，提升工具使用性能。

FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents

👍 16

08/19 08:00

Language model agents now execute bounded tasks reliably. Whether they can sustain effective decision-making over long horizons, where actions have cumulative consequences and the environment responds to their choices, remains largely unmeasured. FM-Bench (Football Management Benchmark) measures thi

中文介绍 提出FM-Bench（足球管理基准），评估语言模型在长期决策中应对竞争智能体、累积后果的持续决策能力。

Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning

👍 15

08/19 08:00

JEPA-style latent world models can use Euclidean distance to a goal latent as the cost for model-predictive control (MPC). Strong decoding of task variables, however, does not guarantee that this particular cost ranks candidate action sequences by real task progress. We call the latter property deci

中文介绍 针对JEPA潜世界模型中决策度量与目标不对齐问题，提出动作条件目标，用于MPC规划，提升决策度量与目标的一致性。

FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving

👍 14

08/20 16:02

Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. Our previous work, FlashPrefill, mitigates this cost through instantaneous pattern discovery a

中文介绍 提出FlashPrefill V2，采用块稀疏预填充注意力，降低长上下文LLM服务中预填充阶段的算力成本，提升效率。

Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion

👍 14

08/14 08:00

High-quality creative writing data for large language models (LLMs) remains dominated by story-centric data, limiting models' ability to follow the structural and functional conventions of diverse creative formats. We propose an attribute-guided genre expansion framework for scaling creative writing

中文介绍 针对创意写作数据以故事为主、缺乏多样性，提出属性引导的体裁扩展框架，规模化生成多样创意内容，提升模型泛化。

Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See

👍 13

08/18 21:09

Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource language. On accuracy benchmarks almost nothing happens, and the benchmark itself is noise at this scale: changing only the random seed moves the sc

中文介绍 研究在低资源语言中推理时，SFT和RL的作用，发现准确率基准在随机种子下不稳定，强调评估的可靠性问题。

VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation

👍 11

08/19 08:00

Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual quality dimensions, including audio quality, visual fidelity, and synchronization. However, these metrics evaluate perce

中文介绍 提出VA-Judger，基于人类偏好反馈的奖励建模，用于联合视频-音频生成模型的后训练，改善多维度质量评估。

Update on our post-training effort

@gabepereyra · 11.4K 粉丝 · 616.8K 阅 · 507 赞 · 99 转

08/20 23:00

Authors: @nikogrupen @ItsJulioPereyra @calvincongelado @vtrengarajan @gabepereyra Over the past six months, Harvey’s research agenda has focused on two goals: Building frontier legal intelligence

中文介绍 Harvey 研究团队复盘过去六个月的 post-training 工作，聚焦构建前沿法律智能。

How To Set Up Grokbot The Right Way So It Runs Your Business While You Sleep In 2026

@heynavtoor · 149.3K 粉丝 · 161.9K 阅 · 550 赞 · 93 转

08/20 20:49

Elon Musk just told his followers to try Grokbot after a power user showed it replaced his $10,000 Mac Mini local AI setup (Elon on X, Aug 16). Gavin Baker says his AI usage went up about 100x after

中文介绍 如何正确配置 Grokbot 以在 2026 年自动运营业务。提到马斯克推荐、替代 1 万美元 Mac Mini 本地 AI 设置，以及 Gavin Baker 的 AI 使用量增长 100 倍。

Building software factories (with no slop)

@dzhng · 13.3K 粉丝 · 137.6K 阅 · 502 赞 · 48 转

08/20 09:39

The amount of code being written today far outpaces our ability to review it. That part isn't controversial. What's more interesting is that we're visibly losing — the amount of AI slop in modern

中文介绍 探讨构建软件工厂而避免 AI 生成垃圾代码。指出代码量超出审阅能力，现代代码库中 AI 生成内容泛滥，我们正在失败。

Agentic coding is now multiplayer: Introducing Slack Code

@SlackHQ · 434.3K 粉丝 · 86.9K 阅 · 512 赞 · 44 转

08/20 20:28

AI coding is now a team sport. Code channels bring software development out of private tabs, so teams and agents can write, review, and ship code together, in the open. Slack is where agents become

中文介绍 Slack 推出 Code Channels，将软件开发从私人标签页中解放出来，让团队和代理共同编写、审阅和发布代码。

AI Engineering Skills Map: Building and Deploying AI Applications

@AndrewYNg · 1.8M 粉丝 · 62.4K 阅 · 1.2K 赞 · 189 转

08/22 00:37

I previously wrote about our AI Engineering Skills Map, with the highest level skills being (i) Building and deploying AI applications, (ii) Software engineering fundamentals, (iii) Using coding

中文介绍 Andrew Ng 回顾 AI 工程技能图谱，强调最高级技能包括构建和部署 AI 应用、软件工程基础和使用编码工具。

RL Policy Churn

@ID_AA_Carmack · 3.7M 粉丝 · 58.8K 阅 · 577 赞 · 40 转

08/21 03:01

I have a good theory about this now. The Phenomenon of Policy Churn https://arxiv.org/pdf/2206.00730 The classic exploration method in RL is “epsilon greedy”, where the agent normally takes the “greedy” action

中文介绍 John Carmack 分享对强化学习中“策略震荡”现象的理论，并引用 arXiv 论文，对比 epsilon-greedy 等经典探索方法。

Grok Bot vs. Hermes: They Look Similar. Underneath, They’re Making Very Different Bets.

@themahis · 4.7K 粉丝 · 43.0K 阅 · 515 赞 · 37 转

08/20 23:59

One is trying to make AI teammates feel like a managed product. The other is turning the agent itself into an open, composable runtime. Research note — August 20, 2026: For this comparison, I

中文介绍 对比 Grok Bot 与 Hermes：一个将 AI 队友当作受管产品，另一个将代理做成开放可组合的运行时。

5 design patterns for long-horizon agent harness

@GoogleCloudTech · 1.3M 粉丝 · 42.9K 阅 · 506 赞 · 87 转

08/20 09:23

Any agent can look brilliant on a one-shot task. Give it a week of real work and it starts to fall apart. "Long horizon" means the agent keeps going across days and dozens of sessions instead of

中文介绍 Google Cloud 分享 5 个长时任务代理架构设计模式，强调代理需跨天、跨会话持续工作。

System Design for Agent Systems (Part 1)

@kmeanskaran · 13.9K 粉丝 · 32.9K 阅 · 518 赞 · 66 转

08/20 21:52

Put a frontier model into a badly designed agent system and you get a more articulate failure. Nearly all of the engineering sits outside the model, in the scaffolding that has come to be called the

中文介绍 讨论代理系统设计第一部分：模型外的脚手架工程至关重要，设计不当会导致更聪明的失败。

[AINews] 10% worse, 100x cheaper, 10000x faster: Why Simulation is taking over

Latent Space · 08/22 15:36

Did you think RSI stopped at model training?

中文介绍 本文讨论模拟技术正在取代传统模型训练，提出“性能差10%、成本低100倍、速度快10000倍”的新范式，认为模拟不仅在模型训练阶段，更可能在更广泛领域占据主导地位。

The Evolution of the Agent Harness

Latent Space · 08/22 15:30

Models keep absorbing the harness into their weights — soon, it will be a harness for human attention rather than for the model.

中文介绍 文章探讨智能体控制器（Agent Harness）的演变，指出模型正不断将控制器融入自身权重，未来可能成为人类注意力的接口，而非仅用于模型控制。

Simulation: the new Scaling Law — Joon Sung Park, Simile AI

Latent Space · 08/22 07:37

Simile’s CEO about his journey from the viral Generative Agents to creating 8 Billion Digital Twins of every living human... and why it’s gone from fun exploration to very serious business.

中文介绍 Simile AI CEO Joon Sung Park分享从病毒式传播的生成式智能体研究，到为每个活人创建80亿数字孪生的历程，表示该领域已从趣味探索转向严肃商业应用，并认为模拟是新的扩展定律。

From Atari to EVE Online: Building on 15 Years of AI Research in Games

DeepMind Blog · 08/21 19:59

Google DeepMind partners with game studios to prototype breakthrough AI gameplay.

中文介绍 Google DeepMind宣布与游戏工作室合作，在15年游戏AI研究基础上，从Atari到EVE Online，原型测试突破性AI游戏玩法，推动AI在游戏领域的应用。

[AINews] Poolside gets $12B reverse-execuhire to NVIDIA; founders stay for $1B, employees go for $6B, Infraco scaling to 7GW neocloud

Latent Space · 08/21 13:45

Yes, we’re confused too.

中文介绍 AI新闻：Poolside获NVIDIA 120亿美元反向收购，创始人留任获10亿美元，员工获得60亿美元，同时其基础设施公司Infraco扩展至7GW规模的云端，交易细节令人困惑。

not much happened today

Smol AI News · 08/21 13:44

**Ox Alpha** emerged as a mystery model with strong coding and agentic performance, likely a **Zhipu/GLM-family** model such as **GLM-5.3 Vision**. Analysts suggest its gains come from post-training and infrastructure improvements rather than sheer size, based on the **743B base** of **GLM-5.2** wit

中文介绍 今日动态：神秘模型Ox Alpha表现出色，推测为智谱GLM系列（如GLM-5.3 Vision）的变体，基于743B基础模型，分析师认为其提升来自后训练和基础设施优化而非规模。

Measuring benchmark optimization in speech recognition

Hugging Face Blog · 08/21 08:00

中文介绍 Hugging Face博客文章讨论语音识别中基准测试优化的测量方法，探讨如何评估模型在标准测试集上的过拟合与真实性能提升。

ChatGPT Apple Messages 💬, Anthropic’s meeting recorder 💼, Mistral Agentic Search 🔍

TLDR AI · 08/21 08:00

中文介绍 AI新闻摘要：ChatGPT集成Apple Messages，Anthropic推出会议记录工具，Mistral发布代理搜索功能，多家AI公司更新产品。

The /wayfinder Skill: Navigating the “Fog of War” of Planning

Latent Space · 08/21 04:59

Matt Pocock tells us about his /wayfinder skill, for greenfield projects or for when the way forward is unclear.

中文介绍 Matt Pocock介绍其/wayfinder技能，用于新项目或方向不明时应对规划的“战争迷雾”，提供导航与决策支持。

Up to 3.2x Faster Inference with LFM2.5-DSpark

Hugging Face Blog · 08/21 00:52

中文介绍 Liquid AI发布LFM2.5-DSpark模型，推理速度提升高达3.2倍，优化了计算效率，适用于大规模部署。

Debates over AI consciousness are a trap

MIT Tech Review AI · 08/20 23:42

“Runaway” AI, “rogue” agents, and “autonomous” actors—the current rhetoric would have you believe that AI agents are not only awake and aware, but angry at their creators. Prominent tech leaders such as Demis Hassabis, Dario Amodei, and Sam Altman push for regulation of these seemingly “superhuman”

中文介绍 MIT科技评论文章指出，关于AI意识的争论可能是个陷阱。当前“失控AI”“流氓代理”等言论误导公众，而Demis Hassabis、Dario Amodei等领袖推动监管，但需谨慎对待。

Unlocking hidden revenue streams with market models

MIT Tech Review AI · 08/20 17:47

Each day, an airline transports tens of thousands of passengers on hundreds of flights. Often these are not straightforward point-to-point routes, with passengers requiring multiple connections. The airline can consider potentially hundreds of variables to price each of these journeys: demand, seaso

中文介绍 文章探讨航空公司利用市场模型解锁隐藏收入，通过分析数百个变量优化多段航线定价，提升收益管理效率。

Introducing AI Futures

OpenAI News · 08/20 15:00

Introducing AI Futures, a new OpenAI blog exploring how transformative AI could reshape power, governance, the economy, and individual freedom.

中文介绍 OpenAI推出新博客“AI Futures”，探讨变革性AI如何重塑权力、治理、经济和个人自由，展望未来影响。

not much happened today

Smol AI News · 08/20 13:44

**OpenAI** and **Anthropic** expanded their agent platforms with new desktop features, collaborative editing, and composable APIs like Skills and Files API. **OpenAI** rolled out memory and workflow features in the EEA, UK, and Switzerland. **AT&T** revealed that 40% of employee AI usage routes to o

中文介绍 OpenAI与Anthropic扩展代理平台，新增桌面功能、协作编辑和可组合API（如Skills和Files）。OpenAI在EEA、英国和瑞士推出记忆与工作流功能。AT&T透露40%员工使用AI工具。

[AINews] Death of Params: Z.ai CEO Jie Tang on GLM 5.3 and the new Post-training Scaling Law

Latent Space · 08/20 13:17

Every lab CEO is on X now

中文介绍 Z.ai CEO唐杰在X上讨论GLM 5.3，提出“参数死亡”观点，强调后训练扩展定律的重要性，认为模型性能提升不再依赖参数规模。