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 EnvHarness 提出唤醒静态环境以促进智能体学习，针对手工构建环境无法感知智能体弱点、随能力提升而过时的问题。不同于依赖领域专用流程的环境生成方法，EnvHarness 自适应动态生成环境，持续匹配智能体能力，降低对昂贵领域知识的依赖。

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 Zetta ζ 提出面向具身智能的高效闭环训练框架，解决现有智能体框架在物理执行中开环的问题——推理时执行固定技能、回合结束后才反思。通过闭环自我进化机制，在执行过程中持续学习与调整，推动实体智能体实现自我进化。

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 SemaPLC 面向 PLC 代码生成，解决大模型生成的独立程序组织单元能否集成进现有 PLC 工程并正确运行的问题。提出以工程为背景、验证门控的智能体框架，对生成逻辑进行集成验证，超越此前有限测试，提升工业代码生成的可靠性。

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 FACET 解决终端智能体训练中高质量任务合成难的问题。每个任务需耦合指令、初始化环境、参考解和可执行验证器，若生成时假设不一致则任务无效。FACET 保留源意图与可执行状态，使合成任务保持一致，为终端智能体提供可扩展监督信号。

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 Co-RL 提出多智能体强化学习方法，摆脱对可验证奖励等真实监督的依赖。通过多样化的智能体群体，在没有外部标注的情况下让推理能力在交互中自发涌现，降低了 RL 训练中对昂贵标注的需求，扩展了推理强化学习的适用范围。

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 OmniScientist 提出全模态、全学科的 AI 科学家框架，旨在超越仅覆盖研究流程的做法，让 AI 能获取科学发现所依赖的完整证据。它从假设生成、代码执行到论文撰写自动化全流程，同时强调对多模态证据的访问，提升 AI 驱动的科学发现能力。

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

👍 60

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 SWE-bench Science 关注科学软件中的编码智能体评估问题。科学代码故障会危及程序行为乃至科学结论的证据，而现有评测过度强调总体任务成功率。该基准针对科学工程任务，检验编码智能体能否解决影响科研证据的工程问题，揭示面向科学的编码能力短板。

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 SPADE 提出在自适应合成可执行环境中进行自博弈，解决语言智能体训练目标分布固定的问题。现有环境池（手工筛选、静态合成或冻结验证器）不随学习者规模扩展而变化；SPADE 通过自我博弈持续生成多样化、自适应的目标与可执行环境，支撑智能体的持续自我改进。

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本质被单一答案评测掩盖的问题，提出 Top-K prompting 训练与推理范式，训练化学合理性感知的 LLM。使模型不再只给出单个答案，而是生成多个合理候选，并感知化学合理性，改进计算机辅助合成规划中的逆合成预测与评测。

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 MemTrapBench 基准聚焦 LLM 记忆使用中的“认知陷阱”。现有记忆基准只评估信息提取、存储和检索是否正确，忽略了检索到的记忆如何被后续推理使用。该基准通过设计陷阱场景，考察记忆是否误导模型判断，为长期记忆系统的可靠性提供评测。

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 SkillEvo 让智能体技能具备自我更新的进化闭环。现有技能多为手工编写或单次生成，无法从自身引起的交互失败中改进；近期工作虽闭环但反馈仅来自单轮问答。SkillEvo 从多轮交互反馈中获取进化梯度，使技能不断自我更新，降低对手工设计的依赖。

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

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

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

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

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

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

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

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

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

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 法律AI公司Harvey研究团队更新后训练工作进展：过去六个月聚焦两大目标，首要为构建前沿法律智能。作者包括五位核心研究员，属于法律AI模型优化的阶段性公开分享。

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 博主分享如何正确配置Grokbot，让它在2026年替你自动运营业务，睡觉时也能赚钱。马斯克刚向粉丝推荐该工具，称有用户用它替代了1万美元的Mac Mini本地AI；加文·贝克表示自己的AI使用量因此猛增约100倍。

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发布新产品Slack Code，主张AI编码已从单人操作变成团队运动。代码频道让软件开发走出私人页面，团队与AI智能体能在开放环境中共同编写、审查、交付代码，实现真正的协同开发。

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 吴恩达介绍AI工程技能图谱的最新框架，最高层技能包括：构建与部署AI应用、软件工程基础、使用编码工具。适合开发者据此定位自身能力、规划学习路径。

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 卡马克分享对强化学习「策略更替」现象的新理论解释，并链接论文《策略更替现象》。他从经典ε-greedy探索方法讲起，分析智能体在贪心行动与随机探索之间的权衡。

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 研究笔记对比Grok Bot与Hermes：二者看似相似，底层赌注却截然不同。前者试图让AI队友像托管产品一样易用，后者把智能体本身做成开放、可组合的运行时，代表两条不同设计路线。

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 博主开启「智能体系统设计」系列第一篇，核心观点：把前沿模型放进设计糟糕的智能体系统，只会得到更清晰的失败；工程重心全在模型之外的脚手架层。

[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 模拟技术以10%性能损失换取100倍更低成本和10000倍更快速度，正成为AI新趋势；递归自我改进（RSI）并不止步于模型训练阶段，已延伸至更广领域。

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 探讨智能体控制框架（Agent Harness）的演进：模型不断将外部框架内化到自身权重中，未来该框架或将转而服务于人类注意力，而非仅用于约束模型。

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首席执行官Joon Sung Park谈及其从爆款项目Generative Agents到为每个在世人类创建80亿数字孪生的历程，认为模拟已成为新的规模法则，并从趣味探索转向严肃商业应用。

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 谷歌DeepMind宣布与游戏工作室合作，基于15年来从Atari到《EVE Online》的游戏AI研究成果，共同开发原型，推动突破性AI玩法落地。

[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以120亿美元“反向高管雇佣”交易并入NVIDIA，创始人留守获10亿美元，员工分享60亿美元，其基础设施公司Infraco正扩展至7GW规模的新云。

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 神秘模型Ox Alpha亮相，编程与智能体能力突出，疑似为智谱GLM家族（如GLM-5.3 Vision），基于743B参数基座。分析师认为其提升主要来自后训练与基础设施优化，而非单纯扩大规模。

Measuring benchmark optimization in speech recognition

Hugging Face Blog · 08/21 08:00

中文介绍 Hugging Face博客讨论语音识别中基准优化的衡量方法，分析如何区分模型真实能力提升与针对基准测试的过拟合优化。

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

TLDR AI · 08/21 08:00

中文介绍 TLDR AI 8月21日要闻：ChatGPT接入苹果信息应用Apple Messages；Anthropic推出会议记录工具；Mistral发布智能体搜索功能。

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在Latent Space分享其/wayfinder技能，旨在帮助开发者在全新项目或方向不明时穿越“战争迷雾”，更有效地进行规划。

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

Hugging Face Blog · 08/21 00:52

中文介绍 Hugging Face博客发布LFM2.5-DSpark模型介绍，称其推理速度最高可提升3.2倍，为大规模部署带来显著效率优化。

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 麻省理工科技评论发文指出，关于AI意识的争论是一个陷阱。当前“失控”“叛逆”“自主”等修辞让人误以为AI代理已有意识并对创造者不满，而包括Demis Hassabis、Dario Amodei、Sam Altman在内的科技领袖正以此推动监管。

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 麻省理工科技评论探讨利用市场模型解锁隐藏收入流。以航空公司为例，其每天运送数万名乘客、涉及大量中转航线，需考虑数百个变量为每段旅程动态定价，模型可优化收益。

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宣布推出新博客栏目AI Futures，聚焦变革性AI对权力格局、治理体系、经济形态和个体自由的潜在重塑。

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扩展智能体平台，新增桌面功能、协作编辑及Skills和Files API等可组合接口；OpenAI还在欧洲经济区、英国和瑞士推出记忆与工作流功能。

[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 Latent Space的AINews报道，Z.ai首席执行官唐杰（Jie Tang）谈GLM 5.3与新的后训练规模法则，提出“参数终结”观点，强调后训练阶段正成为AI性能提升的关键。