2026-08-22

EnvHarness: Awakening Static Worlds for Agent Learning

👍 245

08/19 20:00

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 论文提出了一种名为EnvHarness的方法，以克服大语言模型（LLM）在静态手工构建环境中学习的局限性。该方法通过自动生成动态、适应性环境来增强代理的学习能力，避免代理因环境静态而无法自我改进。研究表明，EnvHarness在多种任务中显著提升了代理的适应性和学习效率，促进了强化学习领域中环境生成方法的发展。意义：对于Agent和环境交互研究具有重要影响。

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

👍 141

08/16 20:00

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提出了一种高效的闭环设计，以提升化身智能体在物理执行中的学习能力。与传统的开放式学习模式不同，该方法实现了在任务执行过程中实时反馈和调整，确保智能体在动作执行中不断优化。实验结果表明，与目前的方法相比，代理在闭环学习中的性能有明显提升，拓宽了多智能体系统的应用潜力。意义：推动了物理智能体研究向闭环优化的转变。

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

👍 115

08/18 20:00

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提出了一种针对PLC代码生成的项目导向验证门控代理方法，提升了生成代码的整合与运行有效性。该方法通过结合大型语言模型和项目上下文进行验证，以实现对PLC项目中逻辑的全面检验。实验结果显示，SemaPLC在多项任务中提高了代码集成的准确性和运行的有效性，为工业自动化领域的代码生成带来了新的可能。意义：对工业自动化与编程自动化研究具有重要价值。

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

👍 111

08/18 20:00

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解决了终端任务合成中的可扩展可执行监督问题，通过建立一套高质量任务生成管道来提升合成的终端任务的质量。该方法确保每个任务均具有明确的指令、初始化环境及验证器，从而克服了任务生成中的一致性问题。结果表明，FACET在多种任务场景下提升了任务执行的成功率，推进了可执行任务合成的研究进展。意义：对提高人工智能模型的自主任务执行能力具有重要驱动作用。

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

👍 91

08/18 20:00

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提出了一种无监督的多智能体强化学习方法，探讨了多样化群体如何有效提升推理能力。与依赖真实监督的传统方法不同，该研究展示了在不需要大量标注数据的情况下，智能体如何从多样化中学习。实验表明，该方法在解决复杂推理任务时的表现优于基线模型，推动了无监督学习在强化学习领域的应用前景。意义：对Agent推理能力的增强具有实际意义。

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

👍 88

08/12 20:00

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引入了一种全模态的AI科学家模型，能够自动化完成从假设生成到手稿准备的完整研究工作流。此模型结合了多领域的知识，提升了研究工作的全面性和效率。成果证明，OmniScientist在科研流程的各个环节中不断优化了效率，为科学研究自动化开辟了新视野。意义：具有推动科学研究方法现代化的潜力。

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

👍 58

08/19 20:00

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评估了编码代理在科学任务中的表现，探讨了科学代码故障对科学结论的影响。该研究通过多个综合任务评估编码代理的成功率，揭示了编码缺陷可能导致的科学证据失效，推动了软件工程和科学研究的交叉分析。结果显示，现有评估方法对代理的综合能力重视不足。意义：对科学计算和软件可靠性研究的信号意义重大。

SPADE: Self-Play in Adaptive Synthetic Executable Environments

👍 47

08/18 20:00

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引入了一种自适应合成可执行环境中的自我游戏方法，以帮助语言代理持续自我改进。该方法通过生成多样化、适应性目标的动态环境，避免了传统训练方式中目标固定的局限性。实验显示，SPADE在代理的学习效率和目标适应性上有显著提升，推动了自我学习代理领域的研究。意义：为Agent的自我优化方法提供了新思路。

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

👍 32

08/18 20:00

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 论文提出了一种Top-K prompting方法，以克服单步反向合成在计算机辅助合成规划中的不足之处。该方法通过提供多种可能的合成路径，增强了系统在进行单步回溯合成时的准确度和多样性。初步实验表明，该方法在合成效率和可行性评价方面优于传统指标，推动了化学合成领域的研究前沿发展。意义：对化学合成的智能化提供了有力支持。

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

👍 31

08/19 20:00

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提出了一种新的基准测试方法，以评估大型语言模型在记忆使用中的认知陷阱。该研究指出，当前的记忆评估方法过于关注信息的正确提取和存储，而忽视了如何恰当地利用这些信息。通过引入新的测试指标，该方法为了解模型的长效记忆提供了新的视角，有助于改善模型的记忆表现。意义：为记忆和长效交互研究开辟了新的研究方向。

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

👍 29

08/12 20:00

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提出了一种自我更新的演化梯度方法，通过多轮交互反馈提升智能体技能的生成和优化能力。与传统的技能生成方法相比，该方法可以实时反映交互中的反馈，促进技能的持续改进。实验证明，SkillEvo显著提高了智能体在复杂交互中的表现，拓展了强化学习在技能演化方面的潜力。意义：为Agent的技能优化提供了新思路和方法。

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

👍 17

08/19 20:00

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 Repo0提出了一种设计驱动的零到全代码生成方法，解决了现有系统对预定义代码库架构的依赖。此方法允许智能体通过自然语言直接构建完整的软件项目，从而提升代码生成的灵活性和效率。实验证明，Repo0在多项代码生成任务中表现优越，推动了智能代码生成技术的发展。意义：为智能体在软件开发中的应用提供了新路径。

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

👍 17

08/13 20:00

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 AdaPop方法提出了一种基于流行度的自适应学习策略，旨在改进大型语言模型的去学习过程。此方法根据训练数据频率调整梯度压力，从而有效增强了对热门知识的去学习能力。研究表明，该方法在多个去学习任务中显著提高了模型性能，推动了人工智能模型更新和适应的灵活性研究。意义：为知识管理与自适应学习开辟了新方向。

Looped Language Models Improve Compositional Tool Calling

👍 16

08/16 20:00

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 该研究探讨了循环语言模型在组合工具调用中的应用，旨在提升智能体在复杂API调用中的推理能力。通过协调多个API调用并保持中间状态，该方法有效增强了工具使用的灵活性和连贯性。实验证明，循环语言模型在处理复杂任务中的表现优于常规模型，为智能体工具使用与推理的结合开辟了新的可能性。意义：对智能体的工具使用能力提升提供了重要启示。

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

👍 16

08/18 20:00

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 FM-Bench提出了一种新的基准，用于评估语言模型代理在长时间决策中的效果，重点关注行动的累积影响及环境反馈。该方法通过量化决策能力，为理解代理在多目标环境中的表现提供了详尽的评估标准。实验结果显示，FM-Bench能够有效反映语言模型在复杂决策中的表现，推动了代理决策能力的研究前进。意义：将促进长期决策和智能体行为研究的深入。

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

👍 15

08/18 20:00

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 该研究提出了一种新方法，旨在解决JEPA风格潜在世界模型中决策度量对模型预测控制的影响。通过对任务变量的强解码，该方法优化了候选行动序列的排名，确保模型在真实任务中更有效。实验表明，该方法不仅提高了准确性，也增强了模型的实际应用潜力，推动了潜在模型在控制任务中的适用性。意义：为模型预测控制领域提供了重要的理论支持。

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

👍 14

08/20 04:02

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 FlashPrefill V2通过块稀疏预填充注意力机制，以解决大型语言模型在长上下文建模中的计算瓶颈。此方法在预填充过程中显著降低了计算复杂度，提升了处理长文本的效率。实验结果表明，该方法在多个长上下文任务中表现优越，为大型语言模型在复杂语言任务中的应用提供了强有力的支持。意义：推动了长文本处理技术的性能提升。

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

👍 14

08/13 20:00

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 该研究提出了一种以属性引导的创意写作体裁扩展框架，以解决现有创意数据集中以故事为中心的局限性。通过扩展多样化的创意格式，模型能更好地遵循不同创作体裁的结构和功能规范。实验结果显示，该方法在创意写作任务中表现优越，有助于提升大型语言模型在创作领域的应用能力。意义：为创意写作生成模型的发展提供了新思路。

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

👍 13

08/18 09:09

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 该研究探讨了混合专家模型在低资源语言上的精确度，对比了微调与强化学习的效果。结果显示，在精确度基准上趋于平稳，且在较低的样本规模下表现出较大的随机性，揭示了现有模型在低资源环境中的适用性限。该发现不仅挑战了现有模型的评估标准，也为低资源语言处理提供了参考依据。意义：对多语言处理技术的发展具有重要潜在影响。

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

👍 11

08/18 20:00

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 VA-Judger针对双视频音频生成模型的奖励建模问题，提出了一种基于用户偏好的反馈方式。通过综合多维品质指标，该方法提升了生成模型的整体性能。研究表明，该方法能够在多个视频音频生成任务中显著提高用户满意度，推动了生成模型质量评价与优化的研究进展。意义：为人机互动生成模型的开发提供了重要启示。

Update on our post-training effort

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

08/20 11:00

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 博主分享了关于研究成果的更新，重点是建立前沿法律智能的研究目标。此内容反映了学术界对于法律技术应用的持续关注和探索。

Turn Grok Bot Into Your CTO

@RayFernando1337 · 37.8K 粉丝 · 169.9K 阅 · 520 赞 · 85 转

08/19 17:54

I've turned Grok Bot into my CTO and I'm no longer the bottleneck for new ideas, bug fixes, or anything involving the project. Prompt to CTO When working on a new project I create a bot and give it

中文介绍 通过将 Grok Bot 作为 CTO，博主解决了项目思路和漏洞修复上的瓶颈。这个案例展示了 AI 工具在提升团队协作和效率方面的实用性。

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 08:49

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 博主介绍了如何有效设置 Grokbot，使其能够在用户休息时自动运作。这一趋势显示了 AI 自动化在商业运营中的潜力。

Building software factories (with no slop)

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

08/19 21:39

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 博主讨论了现代软件开发中代码审查与撰写速率的不平衡，指出 AI 工具的广泛应用导致了代码质量的下降。这个问题引发了行业对改进 AI 工具的关注。

Agentic coding is now multiplayer: Introducing Slack Code

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

08/20 08:28

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推出了团队协作的AI编程新方式，使软件开发变成一种团队运动，强调开放性和协作。这个方向显示了团队开发的未来趋势。

AI Engineering Skills Map: Building and Deploying AI Applications

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

08/21 12:37

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 博主分享了AI工程技能地图，包括构建和部署AI应用的高级技能。这是对AI专业技能需求不断增长的回应，凸显了行业内对专业人才的渴求。

RL Policy Churn

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

08/20 15:01

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 博主提出了关于强化学习策略波动的理论，讨论了经典的探索方法。这反映了针对AI学习过程中的常见问题的深入研究。

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 11:59

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 博主对比了两种 AI 工具的设计理念，指出它们在团队合作与开放性架构上的不同选择，揭示了AI产品发展方向的多样性。

5 design patterns for long-horizon agent harness

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

08/19 21:23

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 介绍了应对长期任务的五种设计模式，博主强调了 AI 代理需要在多次会话中保持实用性的重要性。这反映了开发者对 AI 稳定性和可靠性的共同关注。

System Design for Agent Systems (Part 1)

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

08/20 09:52

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 博主探讨了代理系统设计的关键问题，并指出大多数工程挑战在模型外部，这提示了构建有效 AI 系统所需的基础设施重要性。

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

Latent Space · 08/22 03:36

Did you think RSI stopped at model training?

中文介绍 模拟技术正在迅速发展，其性能提高了10%，但成本降低了100倍，速度提升了10000倍。这一趋势显示出RSI（残差自回归模型）在模型训练之外的潜力。

The Evolution of the Agent Harness

Latent Space · 08/22 03:30

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 AI模型正在逐步吸收人与模型之间的交互界面，未来可能成为专为人类注意力设计的系统。

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

Latent Space · 08/21 19:37

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的首席执行官Joon Sung Park表示，该公司正致力于创建80亿个数字双胞胎，从有趣的探索转变为严肃的商业模式。

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

DeepMind Blog · 08/21 07:59

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

中文介绍 谷歌DeepMind与游戏工作室合作，推动AI游戏玩法的原型开发，积累了15年的研究成果。

[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 01:45

Yes, we’re confused too.

中文介绍 Poolside公司获12亿美元的反向高管招聘，其中创始人保留10亿美元，员工获得60亿美元，Infraco云基础设施扩展至7GW。

not much happened today

Smol AI News · 08/21 01:44

**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 据分析，神秘模型Ox Alpha具备强大的编码性能，可能属于Zhipu/GLM系列，如GLM-5.3 Vision，其改进源于后期训练和基础设施，而非单纯的规模。

Measuring benchmark optimization in speech recognition

Hugging Face Blog · 08/20 20:00

中文介绍 该文章讨论了语音识别中的基准优化。

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

TLDR AI · 08/20 20:00

中文介绍 该消息简要介绍了ChatGPT在Apple Messages中的应用，以及Anthropic的新会议录音功能和Mistral的智能搜索技术。

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

Latent Space · 08/20 16:59

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介绍了他的/wayfinder技能，用于不确定的项目规划中。

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

Hugging Face Blog · 08/20 12:52

中文介绍 LFM2.5-DSpark的推理速度提升了3.2倍。

Debates over AI consciousness are a trap

MIT Tech Review AI · 08/20 11:42

“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 关于AI意识的争论可能是一个误区，知名技术领袖如Demis Hassabis和Sam Altman呼吁对当前AI的监管。

Unlocking hidden revenue streams with market models

MIT Tech Review AI · 08/20 05:47

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 航空公司每一天为数万名乘客提供数百个航班的服务，定价时需考虑成百上千个变量。

Introducing AI Futures

OpenAI News · 08/20 03:00

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推出新的博客AI Futures，探讨变革性AI对权力、治理、经济和个人自由的重塑。

not much happened today

Smol AI News · 08/20 01:44

**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扩展了其智能代理平台，增加了新功能和API，OpenAI在EEA、英国和瑞士推出记忆和工作流程功能。

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

Latent Space · 08/20 01:17

Every lab CEO is on X now

中文介绍 Z.ai首席执行官Jie Tang讨论了GLM 5.3和新的后期训练扩展法，强调各实验室领导者现在都在X平台发声。