2026-08-24

EnvHarness: Awakening Static Worlds for Agent Learning

👍 254

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 针对环境静态、无法适应智能体弱点的问题，提出EnvHarness，通过动态生成与适应环境来提升智能体学习效率，避免人工构建的静态环境限制，实现自动化的环境演化与学习闭环。

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

👍 142

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 针对具身智能体在物理执行中缺乏闭环学习的问题，提出Zetta ζ，一种高效闭环具身训练框架，通过实时反馈和自我演化策略，实现智能体在物理世界中的持续学习与改进，弥补端到端模型的不足。

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缺失的问题，提出SemaPLC，一种项目级PLC代码生成智能体框架，通过验证门控确保生成的代码与现有项目集成并正确运行，提升工业自动化代码的可靠性和实用性。

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

👍 114

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 针对终端任务合成中指令、环境、参考方案与验证器之间不一致的问题，提出FACET方法，通过保持源意图和可执行状态，生成高质量终端任务，提升终端智能体的训练监督质量。

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

👍 92

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 针对强化学习依赖真值监督的问题，提出Co-RL，一种多智能体RL方法，通过多样智能体群体协作，实现无监督推理涌现，减少对昂贵标注的依赖，提升语言和视觉语言模型的推理能力。

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 针对AI科学家工作流覆盖不全的问题，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手稿撰写的完整流程，并提供全证据访问，推动科学发现的自动化。

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

👍 61

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 针对科学编码中工程任务评估缺失的问题，提出SWE-bench Science基准，用于评估编码智能体在解决科学领域工程任务的性能，强调科学代码错误对结论的影响，填补评估空白。

SPADE: Self-Play in Adaptive Synthetic Executable Environments

👍 48

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 针对语言智能体训练环境池固定问题，提出SPADE框架，通过自适应合成可执行环境和自我对弈，生成多样化、自适应的目标，实现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 针对单步逆合成反应中一对多性质评估不足的问题，提出Top-K提示训练范式，结合化学合理性感知，提升逆合成预测的多样性和准确性，改进合成规划。

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 针对LLM记忆使用中的认知陷阱评估缺失，提出MemTrapBench基准，评估模型在检索后使用记忆时的错误，涵盖记忆误用场景，为记忆系统改进提供参考。

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

👍 30

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 针对Agent技能缺乏闭环改进的问题，提出SkillEvo，一种自更新演化梯度方法，通过多轮交互反馈，从失败中学习并不断优化技能，提升智能体的交互表现。

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 针对零到全代码生成中缺乏预定义仓库架构的问题，提出Repo0方法，从自然语言描述直接构建完整软件项目，通过设计驱动流程，提升代码生成的完整性和实用性。

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 针对热门事实更难遗忘的问题，提出AdaPop方法，结合局部token置信度，根据训练数据频率自适应调整梯度压力，提升LLM遗忘效率，尤其针对高频事实。

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

👍 16

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 针对长上下文LLM服务中自注意力二次复杂度瓶颈，提出FlashPrefill V2，采用块稀疏预填充注意力，通过即时模式发现和计算优化，显著降低预填充阶段开销，提升长上下文处理效率。

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 针对循环语言模型在智能体工具调用中的潜力未挖掘问题，研究其在组合工具调用场景下的性能，模型需协调多API调用、维护中间状态，实验表明循环结构改善组合工具调用能力。

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 针对语言模型智能体在长期决策中的能力评估缺失，提出FM-Bench基准（足球管理基准），衡量智能体在长时域管理、累积后果和竞争环境下的决策质量，填补评估空白。

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潜在世界模型中MPC规划成本与真实任务进展不匹配的问题，提出决策度量对齐方法，通过诊断和行动条件目标，确保潜在距离作为成本能正确排序候选动作，提升规划有效性。

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 针对创意写作数据集中于故事类、限制模型适应多样格式的问题，提出属性引导的体裁扩展框架，生成多样创意写作数据，提升LLM遵循不同结构和功能惯例的能力。

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 针对低资源语言推理微调，研究发现准确率基准无法反映变化，随机种子变动即影响结果；SFT和RL对推理能力的影响需超越准确率评估，强调更细致的分析方法。

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

👍 11

08/13 08:00

Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26 embedding models (118M to 14B parameters) on 37 tasks spanning classification, semantic textual similarity (STS), clustering, pa

中文介绍 针对是否用LLM替换文本嵌入管线的问题，进行受控成本比较，评估10个LLM和26个嵌入模型在37个任务上的表现，提供成本效益分析，帮助决策。

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 吴恩达回顾其发布的AI工程技能图谱，将最高层级技能归纳为三方面：构建与部署AI应用、软件工程基础、以及编码工具运用。他强调这些核心能力对实际开发AI产品的重要性，为从业者提供技能提升路线参考。

[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 文章讨论模拟技术正在取代传统模型训练，声称“差10%、便宜100倍、快10000倍”，并解释为何模拟正在接管AI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 本文探讨代理框架的演变，指出模型正不断吸收框架到自身权重中，未来可能成为人类注意力的框架而非模型的框架。

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分享从生成式代理到创建80亿人类数字孪生的历程，强调该领域已从有趣探索转变为严肃业务。

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庆祝游戏AI研究15周年，并与游戏工作室合作，在EVE Online等游戏中原型测试突破性AI玩法。

[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，员工获60亿，基础设施公司扩展至7GW云端。

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表现出色，可能为智谱GLM系列，如GLM-5.3 Vision，基于743B基础模型，优势来自后训练和基础设施改进而非规模。

Measuring benchmark optimization in speech recognition

Hugging Face Blog · 08/21 08:00

中文介绍 Hugging Face博客讨论语音识别基准优化测量方法，旨在更准确评估模型性能。

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

TLDR AI · 08/21 08:00

中文介绍 TLDR AI简报：ChatGPT集成苹果信息，Anthropic推出会议记录器，Mistral推出代理搜索功能。

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介绍其/wayfinder技能，用于新项目或方向不明时在规划的“战争迷雾”中导航。

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

Hugging Face Blog · 08/21 00:52

中文介绍 Liquid AI宣布LFM2.5-DSpark模型推理速度提升最高3.2倍，优化了计算效率。

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科技评论指出AI意识争论是陷阱，批评“失控AI”等修辞，并提及Hassabis、Amodei、Altman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 文章探讨市场模型如何帮助航空公司解锁隐藏收入，通过考虑数百变量为多段旅程定价。

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。

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和Anthropic扩展代理平台，新增桌面功能、协作编辑和Skills/Files API；OpenAI在欧洲经济区、英国、瑞士推出记忆和工作流功能；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唐杰讨论GLM 5.3及后训练扩展定律，称“参数时代已死”，强调后训练的重要性。