2026-08-26

The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search

👍 4

08/24 08:00

As Retrieval-Augmented Generation (RAG) shifts toward diverse portfolio generation, it is stymied by two critical bottlenecks: flawed measurement of evidence utilization, and suboptimal context budget allocation. We resolve both sequentially. To resolve measurement, we expose a pervasive ``diagnos

LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks

👍 6

08/24 08:00

Large language models are increasingly expected to execute complex workflows whose success depends on maintaining interdependent constraints and producing artifacts that satisfy strict end-to-end verification. Yet successful execution experience is typically lost after a single run, forcing subseque

Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports

👍 5

08/24 08:00

Industrial technical reports contain high-value knowledge for maintenance, troubleshooting, and product engineering, but their heterogeneous structure (dense prose, specifications, tables) makes them difficult to index and reason over with standard retrieval and QA pipelines, and no public instructi

Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization

👍 15

08/24 08:00

Policy optimization (PO) for Large Language Models faces a stability--exploration trade-off, currently mediated by an action-side Policy-KL regularizer. This puts practitioners in a double bind: keeping Policy-KL constrains response behavior and consumes the action-side exploration budget, while dro

One Polluted Page Is Enough: Evaluating Web Content Pollution in LLM Recommenders

👍 5

08/24 08:00

Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: LLM recommenders may consume web content that Generative Engine Optimization (GEO) operators have polluted to mislead them. We ask: to what extent do they become unwi

MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks

👍 33

08/24 08:00

As on-device LLM agents evolve into personal copilots, the mobile operating system has become a key testbed for this paradigm, making rigorous capability evaluation essential. Yet existing benchmarks fall into two camps, each with a critical blind spot: GUI-centric benchmarks test surface-level scre

Better Retrieval, Worse Robustness:How Multi-hop RAG Amplifies Upstream ASR Errors

👍 6

08/24 08:00

Speech-based applications pass spoken queries through automatic speech recognition (ASR) before any retrieval module, so ASR errors enter the pipeline as a fixed upstream constraint. We empirically test whether two extensions to standard retrieval-augmented generation (RAG), entity-graph linking and

Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection

👍 7

08/24 08:00

We present a novel approach to efficient LLM harness optimization through adaptive validation task selection. Harness optimization iteratively rewrites the harness code based on validation performance, enabling substantial performance gains without updating the underlying model weights. Existing app

Prime Agent: A Self-Improving RLM Harness

👍 32

08/24 08:00

Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-source harness for long-horizon evaluation and coding-agent workflows. A persistent IPython REPL follows the Recursive Lang

Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA

👍 4

08/24 08:00

A retrieval-augmented QA system can return different answers after an index expansion even when its requested model identifier, prompt, retrieval policy, evidence depth, rendering, and exposed generation controls are held fixed. Aggregate accuracy may hide these changes when gains and losses cancel,

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

👍 172

08/24 08:00

General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, together with state maintenance, failure recovery, and verifiable delivery. We call this working capability: sustained, veri

What AstroPT knows about galaxies, and what that can teach us about LLMs

👍 3

08/23 08:00

Interpretability research increasingly asks when concepts emerge during training and whether linear probes recover real structure, but in language models these claims are hard to validate because language offers little ground-truth ordering of concepts or relationships among them. We propose the use

ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style Holdouts

👍 3

08/23 08:00

Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes. We argue this under-specifies what is being evaluated: the proper unit is a declared model-plus-runtime configuration whose failures can occur in evidence acquisition, runtime routing, safety boundaries, or

AutoResearch: Insight In, Hallucination Out

👍 8

08/23 08:00

Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically grounded. We introduce AutoResearch, a two-stage system that connects Idea Generation with Idea Execution to address both

GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?

👍 12

08/22 08:00

Recent large language models (LLMs) can operate as coding agents that build complete games from natural language requests. Game development is especially demanding because program logic, visual and audio content, interfaces, interaction and playability must function together in one executable artifa

Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

👍 9

08/21 08:00

Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and quantized to 4 bits. Together these steps degrade reasoning, mathematics, coding, and long-context behavior enough to require a recovery, or healing, s

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

👍 52

08/21 08:00

E-commerce live streaming requires omni-modal understanding of noisy, temporally extended streams, where product facts are distributed across speech, video frames, product images, overlaid text, and user queries. We present TLive-Omni, an omni-modal understanding model tailored to live-commerce scen

PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration

👍 3

08/21 08:00

We present PhysCaP, a Physics-Informed Code-as-Policy agent for active perception in robotic manipulation. While vision-language-action policies excel at imitating demonstrations, they rely on passive observation and fail to infer latent physical properties critical for manipulation. PhysCaP augment

Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detection

👍 2

08/20 08:00

Face presentation attack detection (PAD) is traditionally formulated as a face-specific problem, although many of the visual artifacts introduced by print, replay, and recapture processes are not inherently tied to facial appearance. In this work, we investigate whether transferable PAD representati

One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows

👍 9

08/20 08:00

Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling. Yet completing consequential work beyond code requires more than producing a plausible response or valid tool call: agents must gather missing inform

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

👍 27

08/20 08:00

While text-to-3D generation has advanced rapidly, achieving high geometric fidelity at low inference cost remains challenging. Existing text-to-3D methods either decode discrete shape tokens autoregressively or iteratively refine global 3D representations with diffusion or flow models. However, auto

Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources

👍 3

08/20 08:00

Population-level behavior in large-language-model (LLM) agents cannot be characterized by single-agent benchmarks. We introduce PV-SST, a peer-voted social-platform testbed, and report a separately frozen, preregistered matched-exposure experiment spanning four topics, four unused seeds, four open-w

Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference

👍 7

08/20 08:00

Small language models are usually built like large ones and then squeezed onto a CPU afterwards. We did the opposite: we fixed the target first, one user, one token at a time, 4-bit weights, ordinary CPU, and chose the architecture to suit it. The result keeps full attention in only 6 of its 18 bloc

Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress

👍 8

08/19 08:00

On-policy distillation (OPD) has emerged as an effective framework for post-training language models by pairing student-generated trajectories with dense token-level supervision from a teacher. However, OPD implicitly assumes that teacher-derived rewards are an appropriate proxy for reasoning progre

TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration

👍 5

08/18 08:00

Long-context prefill in large language models (LLMs) incurs substantial computation and memory traffic because dense self-attention computes quadratic query-key scores. Existing methods either use a uniform low-precision path or select token interactions, leaving spatial precision routing over hardw

WorldMind: Decoupled Game World Model for State-Aware NPC Behavior

👍 13

08/18 08:00

Game world models have recently demonstrated promising capabilities in generating visually coherent and action-controllable gameplay videos. However, non-player character (NPC) behavior in existing models is either implicitly entangled with video generation or explicitly prescribed through external

Human-Centric Intelligence in the Era of Foundation Models: A Survey

👍 5

08/18 08:00

Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling. Yet it has not fully integrated with foundation models to achieve the comparable progress seen in them. More importantly, recent advances across this bro

ParaTempo: Efficient Parallel Reasoning via Temporal Confidence

👍 32

08/17 19:24

Parallel reasoning improves the accuracy and robustness of large reasoning models by exploring multiple solution paths, but its computational cost grows with reasoning depth and branch count. Existing methods for managing these parallel paths typically rely on final-answer consensus, local token con

Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning

👍 3

08/14 08:00

Electrocardiogram (ECG) recordings are sensitive biomedical data, limiting the ability of hospitals and wearable devices to share raw signals for centralized model training. Federated learning addresses this practical privacy constraint by enabling collaborative model training while keeping raw bios

ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction

👍 15

08/13 08:00

Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for clarification, provide progress updates, or confirm before acting. This flexibility breaks a core assumption behind group-based RL: rollouts compared within a group are no longer guaranteed to be

I gave my Grok Bot 3 X accounts. It got us 69.8M impressions. (full guide)

@chddaniel · 25.5K 粉丝 · 299.3K 阅 · 532 赞 · 26 转

08/24 23:00

69.8M impressions. 321K likes. 319K bookmarks. My brother David and I run these 3 X accounts as one content system. My Grok Bot is behind the ideas, the posts, the replies - everything. One post got

中文介绍 分享如何利用 Grok Bot 在 3 个 X 账户上获得 6980 万次曝光，详细指南包括操作步骤和效果分析。

What if everything goes right for AI? Learnings from the Aluminium trade.

@P_Bonnet · 5.7K 粉丝 · 262.7K 阅 · 519 赞 · 74 转

08/25 00:40

There are countless takes telling us why the AI buildout will result in a bubble that will collapse under its own weight. Some argue we are already in it, and that the subsequent meltdown will be

中文介绍 探讨 AI 发展可能引发的泡沫及其后果，从铝贸易案例中汲取经验教训。

Designing Grok Bot with Grok Bot

@johnbai · 11.7K 粉丝 · 181.3K 阅 · 565 赞 · 29 转

08/25 06:40

At SpaceXAI, we’re building agents that can take an idea and begin making it real. For designers, that changes what’s worth exploring. Design has always been a process of giving form to an idea:

中文介绍 介绍 SpaceXAI 如何使用 Grok Bot 设计智能代理，探讨设计流程的变化。

how i built an SEO/AEO blog engine

@harsehaj · 3.3K 粉丝 · 135.1K 阅 · 507 赞 · 35 转

08/24 08:55

i proposed and executed an engineering project end-to-end this summer as a growth engineering intern at @browserbase: blogEO, an engine that audits, rewrites, and generates SEO/AEO-tailored blogs on

中文介绍 分享在 @browserbase 担任增长工程实习生期间构建 SEO/AEO 博客引擎的全过程。

How to make money with Grok Bot

@EXM7777 · 132.1K 粉丝 · 126.3K 阅 · 504 赞 · 40 转

08/24 23:09

I'm going to show you how Grok Bot works, then hand you 10 workflows that drive real cash for your business... one specialized bot per workflow, running 24/7 on its own computer and i'll say it

中文介绍 展示 Grok Bot 的使用方法，并提供 10 个盈利工作流，每个工作流一个专用机器人，24/7 运行。

Deep Dive: The Next Trillion-Dollar Futures Market

@chamath · 2.4M 粉丝 · 81.1K 阅 · 595 赞 · 52 转

08/25 00:49

“I actually believe a new asset class will be buying futures of compute. We just don’t have enough compute power right now.” - Larry Fink, CEO of BlackRock Recent news moved that prediction closer to

中文介绍 深入探讨下一个万亿美元的未来市场，预测计算力期货将成为新的资产类别。

17 Skills I Would Install on a Fresh Hermes Setup (10x Powerful Hack)

@FareaNFts · 66.2K 粉丝 · 43.7K 阅 · 534 赞 · 39 转

08/23 22:49

If I wiped Hermes tomorrow and started from zero, I would not open a blank chat and "figure it out." I would install skills first. A raw Hermes install is smart. A skilled Hermes setup is unfair.

中文介绍 分享在 Hermes 设置中安装 17 个技能的技巧，实现更强大的功能。

What is harness engineering and why should I care?

@GoogleCloudTech · 1.3M 粉丝 · 35.3K 阅 · 526 赞 · 72 转

08/25 04:30

How do you ship a software product with 0 lines of manually-written code? A friend asked me this today, and I realized I didn’t have a simple answer. So I dug deeper. It turns out the answer is in how

中文介绍 解释什么是 harness engineering，以及为何值得关注，探讨无代码软件产品的交付。

The Zero to Employable AI Engineering Roadmap

@_jaydeepkarale · 31.1K 粉丝 · 24.7K 阅 · 506 赞 · 86 转

08/24 21:46

A phase-by-phase path into AI engineering, with the specific courses, docs, and books worth your time at each stage, not just a list of skills to Google later Most AI engineering roadmaps are skill

中文介绍 提供进入 AI 工程领域的逐步路线图，包括每个阶段值得学习的课程、文档和书籍。

Granite 4.2 LLMs: How They're Built

Hugging Face Blog · 08/25 23:14

中文介绍 Hugging Face 发布 Granite 4.2 LLMs 构建方法。

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

Hugging Face Blog · 08/25 19:39

中文介绍 Hugging Face 推出压缩模型 Quantization-Aware Healing，性能超越原始版本。

I spent a day at a robot “carnival” in Shanghai. Here’s what I saw.

MIT Tech Review AI · 08/25 17:00

Humanoid robots are having a moment in China. The popular machines are part of the country’s strategy to bring artificial intelligence into daily life. Embedding the technology into physical systems—an idea called embodied AI—was a key facet of China’s latest five-year plan, and companies here are a

中文介绍 中国上海举办机器人“嘉年华”，体现将人工智能融入日常生活。

The full stack behind abundant intelligence

OpenAI News · 08/25 15:05

OpenAI CFO Sarah Friar explains how advances across chips, compute, models, and products compound to deliver more useful intelligence at greater scale and lower cost.

中文介绍 OpenAI CFO Sarah Friar 解释了全栈技术如何提升智能规模和降低成本。

Jalapeño’s first results show industry-leading speed and efficiency in AI inference

OpenAI News · 08/25 15:00

Jalapeño is a custom inference chip from OpenAI that delivers faster, more power-efficient AI inference, with higher throughput and lower latency for modern models.

中文介绍 OpenAI 的定制推理芯片 Jalapeño 显示行业领先的速度和效率。

[AINews] Andrew Ng gets into AI Engineering

Latent Space · 08/25 10:50

An industry legend starts covering the inevitable!

中文介绍 Andrew Ng 进入 AI 工程领域。

Disrupting a new covert influence campaign from Russia

OpenAI News · 08/25 08:00

OpenAI banned Russia-origin accounts using AI to promote a fake Israel-based think tank and a “sovereignty” index praising Russia and criticizing the West.

中文介绍 OpenAI 打击俄罗斯的新秘密影响宣传活动。

Introducing the Admin plugin for ChatGPT Work and Codex

OpenAI News · 08/25 08:00

Use the Admin plugin for ChatGPT Work and Codex to analyze workspace usage, manage members and permissions, adjust limits, and act on admin requests.

中文介绍 OpenAI 推出 ChatGPT Work 和 Codex 的管理员插件。

Wire It, Run It, Deploy It: AI Workflows in Gradio

Hugging Face Blog · 08/25 08:00

中文介绍 Hugging Face 提供 Gradio AI 工作流程指南。

Nvidia’s Groq chip ⚡, frontier economics 💰, Ox Alpha mystery 🕵️

TLDR AI · 08/25 08:00

中文介绍 Nvidia Groq 芯片、前沿经济学和 Ox Alpha 的神秘故事。

How to encourage smarter AI use in the classroom

MIT Tech Review AI · 08/24 22:20

This article is from Making AI Work, MIT Technology Review’s limited-run newsletter examining how to apply LLMs across industries. To receive it in your inbox, sign up here. Chatbots took many schools by surprise upon their release a few years ago. Suddenly, students carried an app in their phones t

中文介绍 如何鼓励教室中更智能的 AI 使用。

Advancing price-performance for developers with GPT‑5.6 in Kiro

OpenAI News · 08/24 20:00

GPT‑5.6 is now available in Kiro, helping developers plan, build, review, and test software with better price-performance.

中文介绍 OpenAI GPT-5.6 在 Kiro 上提供更好的价格性能。

Kids outlearn AI—and we still don’t know why

MIT Tech Review AI · 08/24 17:00

People have been talking to each other for at least 100,000 years, as best we can tell. And in all that time, there has been only one thing in the world that could learn a human language to perfect fluency: a human child. Now there are two. Four short years after the release of ChatGPT,…

中文介绍 孩子在学习语言上超越了 AI，原因尚不清楚。

not much happened today

Smol AI News · 08/24 13:44

**Agent harnesses** are becoming a key optimization focus, with NVIDIA research showing traditional skill checks poorly predict agent usefulness and proposing a new metric called **"Skill Lift"**. Open-source implementations of **persistent and self-modifying agents** like **Headlong** and **exo** e

中文介绍 今天没有发生太多事情，Agent harness 成为关键优化焦点。

DeepSeek Flash Vision 👀, Claude Mythos security 🛡️, inside Grok Bot 🤖

TLDR AI · 08/24 08:00

中文介绍 DeepSeek Flash Vision、Claude Mythos 安全性和 Grok Bot 内部视角。