2026-09-03

Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall

👍 1

09/01 08:00

Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervision from stronger teachers, but whether its benefits are consistent across training stages remains unclear. Through controlled experiments, we find that forward Kullback-Leibler (KL) distillation--the

DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation

👍 2

09/01 08:00

Commercial short-drama production follows a multi-stage chain: script, storyboard, keyframe imagery, shot-level video, and the finished short drama. Most existing benchmarks evaluate solely the video-generation stage using pre-authored inputs instead of real upstream pipeline outputs. This leaves tw

From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix

👍 31

09/01 08:00

Data-residency constraints force enterprises to self-host LLMs, but continuous adoption of newer models without decommissioning their predecessors expands the serving fleet, fragmenting a finite GPU pool. We consolidate traffic from over 200 internal applications onto a single model by closing quali

DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory

👍 14

09/01 08:00

Self-play is an effective paradigm for language-model self-evolution, but without guidance, solver performance can plateau or decline across rounds. Unguided methods steer question generation with signals such as difficulty, learnability, or diversity. These signals keep questions challenging and va

Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement

👍 10

09/01 08:00

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually impro

StudentSim: Training LLM-based Student Simulators

👍 458

09/01 08:00

AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulators can provide this signal as a proxy, yet existing approach

Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching

👍 21

09/01 08:00

Multimodal Large Language Models (MLLMs) are strong perceivers of images and video. We ask how far that reach extends into acting: dropping an MLLM directly into a drone's control loop, with its entire action space declared solely in the prompt. Recent systems approach this setting but increasingly

Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs

👍 7

09/01 08:00

Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message routing, output formatting, and termination signals, on which the underlying code re

EM^2Mem: Event-Centric Multimodal Memory for Large Language Models

👍 9

09/01 08:00

Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as isolated fragments. Although searchable, such fragments are not generation-ready: language models must reconstruct cross-mo

The Safeguard Worked. Is the LLM System Safer?

👍 3

09/01 08:00

Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control performed on the requests it was tested on. A deployment has to answer a different question: how much help with harmful tasks the service still gives an at

Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data

👍 3

08/31 08:00

Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI is deploying LLM agents that reason over this data to answer complex questions for every knowledge worker. Agents can do this today, but at prohibiti

Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell You

👍 4

08/31 08:00

Test-time adaptation (TTA) typically assumes that model parameters can be updated at inference time. This assumption is restrictive for inference-only accelerators, frozen or third-party models, and memory-constrained deployments, and standard BatchNorm-based TTA configurations may also become inact

Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry

👍 3

08/31 08:00

Multimodal geometry reasoning requires VLMs to extract precise visual relations and preserve them through multi-step deduction. Existing free-form traces obscure the decisions that determine the answer, and trajectory-level reinforcement learning distributes a single terminal signal across the entir

Agents in the Large: Perception-Centered Architecture for Persistent Agents

👍 8

08/31 08:00

Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and decision-making procedures, enabling agents to reason and act in interactive environments. Existing frameworks largely cast these agents as systems for solving user-specified, bounded ta

E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation

👍 6

08/31 08:00

Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns. Their evolving dynamic environments and long-range dependencies require Large Language Models (LLMs) to continually explore, learn from experience, and adapt their policies over thousands of steps. We introduce E-

Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering

👍 26

08/31 08:00

A central bottleneck in multi-hop Question Answering (QA) is that the granularity at which a question is expressed often differs from the granularity at which corpus evidence is retrievable. Existing methods address this mismatch by imposing fixed graph structures over the corpus, by iteratively ref

Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions

👍 1

08/31 08:00

End-to-end weather forecasting systems produce skillful global gridded and station forecasts directly from raw Earth observations, replacing the numerical weather prediction pipeline, including data assimilation, at a fraction of its cost. These systems are deterministic and issue no uncertainty. He

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation

👍 26

08/31 08:00

Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments. Modern vision-language models (VLMs) already encode spatial priors for visual grounding, spatial reasoning, and pointing, but these capabilitie

Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions

👍 12

08/31 08:00

Strategic deception by LLM and VLM agents has emerged as a central AI alignment and safety concern. Social-deduction games (where each player holds a hidden role and communicates with others to deduce identities) serve as the canonical testbed, particularly in multi-agent settings. Existing testbeds

Verification-Aware Training for Speculative Decoding

👍 5

08/31 08:00

Speculative decoding accelerates large language model inference by using a draft model to generate candidate tokens, which are verified by the target model in a single forward pass. Verification proceeds sequentially and discards every position from the first rejection onward, yet existing draft tra

CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions

👍 4

08/29 08:00

Chain-of-thought (CoT) reasoning has dramatically improved large language models (LLMs) by allowing them to decompose problems into intermediate steps. While CoT is widely effective for linguistic tasks, text-only CoT forces models to serialize visual problems into awkward prose. Although architectu

Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered

👍 10

08/29 08:00

Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness tests often place explicit bias cues in the user message, while agents may encounter preferences through tool returns or raw artifacts. We introduce F

EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants

👍 4

08/29 08:00

Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests evolve. We introduce EvoGenUI-Bench, a benchmark for multi-turn interface maintenance comprising 150 five-turn tasks and 750 turns across three scena

Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models

👍 3

08/29 08:00

Recent work on image content manipulation based on vision-language pre-training models has been effectively extended to text-driven 3D scene editing. However, existing schemes for 3D scene editing still have certain shortcomings, hindering their further development as interactive design tools. Such

Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase

👍 25

08/29 08:00

Organizations often develop and maintain portfolios of related applications: independently deployable codebases that share substantial domain logic, interface patterns, or operational conventions. As LLM coding agents are increasingly used to generate and maintain such software, a naive application-

Evaluating the Hidden Costs of Personalization in Large Language Models

👍 25

08/28 08:00

While Large language models (LLMs) incorporate user personalization signals to improve usability and helpfulness, they increasingly shift from providing balanced, informative responses toward optimizing for user satisfaction when conditioned on personal context such as conversation history, inferred

AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling

👍 16

08/27 08:00

LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely unexamined. We present AgentJudgeBench, the first benchmark to systematically study LLM-as-a-judge reliability for agentic tool-calling over workflow

UI-Venus-2 Technical Report

👍 55

08/27 08:00

Multimodal GUI agents have emerged as a promising paradigm for digital task automation, yet transitioning from benchmark-oriented models to dependable real-world applications remains challenging due to limited environment coverage, brittle task construction, and unreliable reward verification. In th

Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching

👍 6

08/27 08:00

Image retrieval has traditionally been formulated as a point-wise matching problem, where each candidate image is scored in isolation. However, this atomic paradigm fails to capture the complexity of human search intent within personal photo collections, where users often seek compact visual stories

InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal

👍 6

07/21 08:00

Generating professional scholarly content, such as peer reviews and rebuttals, requires an intricate synergy between domain reasoning and factual grounding. This work presents a comprehensive framework for the development and evaluation of specialized scholarly agents, InternReviewer and InternAdvoc

Nobody is talking seriously about AI demand

@giovannicatt3 · 1.4K 粉丝 · 142.0K 阅 · 507 赞 · 56 转

09/01 23:51

AI capex for 2028 is forecast to be larger than the budget of France. Frontier AI labs’ revenue ramp justifies almost any number. Reflexivity in AI demand is a double-edged sword, and it's now a good

中文介绍 分析AI需求预测，指出2028年AI资本支出可能超过法国预算，强调AI需求自反性是一把双刃剑。

Compilers 2.0: AI as stochastic optimizer

@cdleary · 2.3K 粉丝 · 100.3K 阅 · 533 赞 · 66 转

09/02 04:00

There has been a lot of discussion following the presentation of the Jalapeño MLA kernel at HotChips and subsequent commentary by SemiAnalysis. As OpenAI’s hardware team, we just barely touched on

中文介绍 探讨Jalapeño MLA内核在HotChips上的展示及其后续评论，提及OpenAI硬件团队对AI随机优化器的初步探讨。

Department of War Launches OpenAI's ChatGPT Mil on GenAI.mil

@DoWCTO · 104.9K 粉丝 · 86.1K 阅 · 663 赞 · 139 转

08/31 22:25

The Department of War today launched OpenAI's ChatGPT Mil, marking it as the next frontier AI capability housed on GenAI.mil, the Department's premier generative AI platform. This

中文介绍 美国国防部推出OpenAI的ChatGPT Mil，作为GenAI.mil平台上的下一代AI能力。

Agentic Engineering Setup (after 2,000+ hours)

@DavidOndrej1 · 67.4K 粉丝 · 68.7K 阅 · 513 赞 · 40 转

08/31 21:59

Over the past 3 years, I've spent well over 2,000 hours coding with AI, and I've personally interviewed some of the most productive people in the space of Agentic Engineering. Below is my full Agentic

中文介绍 分享超过2000小时AI编码经验，介绍Agentic Engineering的设置和高效实践。

Grok Bot for Engineering

@lingxi · 7.0K 粉丝 · 64.4K 阅 · 629 赞 · 44 转

09/01 02:31

I’m a SpaceXAI engineer building Grok Bot with Grok Bot. Think of Grok Bot as a highly capable engineering intern, with its own computers, that can manage coding agents and learn from how you work. It

中文介绍 介绍Grok Bot，一款具备自身计算机，可管理编码代理并学习用户工作方式的工程助手。

7 Grok Bots for Marketing

@irabukht · 18.4K 粉丝 · 63.3K 阅 · 536 赞 · 28 转

09/02 07:39

18 things to know and 7 paste-in prompts for running ads, SEO and GEO on Grok Bot. Collected from 1,000+ marketers in our community. Most of us use Grok Bot to run marketing work end to end: Weekly

中文介绍 提供7个Grok Bot营销使用提示，收集自1000多位营销人员，涵盖广告、SEO和GEO等全流程工作。

Department of War Launches Starshield AI's Grok for Government on GenAI.mil

@DoWCTO · 104.9K 粉丝 · 57.5K 阅 · 924 赞 · 174 转

08/31 23:09

The Department of War today launched Starshield AI's Grok for Government, expanding the suite of frontier AI capabilities on GenAI.mil, the Department's premier generative AI platform.

中文介绍 美国国防部在GenAI.mil平台上推出Starshield AI的Grok for Government，扩展前沿AI能力。

Your AGENTS.md is holding you back

@posthog · 24.3K 粉丝 · 43.7K 阅 · 503 赞 · 33 转

09/01 02:01

Context engineering used to focus on adding information that base models lacked: But then the models kept getting better. Now, the same context your agents couldn’t function without can make them

中文介绍 指出基础模型不断进步导致上下文工程的重要性降低，强调上下文可能成为限制因素。

Introducing agentic video understanding with Gemini

@GoogleAIStudio · 197.2K 粉丝 · 37.4K 阅 · 522 赞 · 48 转

09/02 02:02

Our new agentic feature for video analysis cuts costs by up to 66% and reduces token consumption by up to 88% while boosting accuracy. Today, we’re launching agentic video understanding across our

中文介绍 推出Gemini视频分析的新功能，降低成本并提高准确性，同时减少token消耗。

Using Grok Bot: 8 templates to get inspired

@mattyp · 57.4K 粉丝 · 29.7K 阅 · 508 赞 · 40 转

09/02 01:03

Templates are now available for Grok Bot, so I wanted to share my favorites. Templates contain the skills, memories, and official @bot plugins from your bots. When you use a template, you get a copy

中文介绍 分享Grok Bot的8个模板，包含技能、记忆和官方插件，以激发灵感。

A Lagrangian View of Flow Matching

@docmilanfar · 115.8K 粉丝 · 26.0K 阅 · 512 赞 · 56 转

08/31 12:36

This is a pedagogical post meant to offer an intuitive, bottom-up perspective on Flow Matching. If you have ever wondered why some models require hundreds of iterative steps to generate an image while

中文介绍 从拉格朗日视角介绍Flow Matching，解释为何某些模型需要数百次迭代步骤生成图像。

From rg to zg: Local Search Beyond Keywords

@QwenDevs · 10.9K 粉丝 · 21.4K 阅 · 509 赞 · 55 转

09/02 22:30

Summary: The information humans and agents need is often scattered across large numbers of local files, making it difficult to locate accurately and efficiently. zg (zvec-grep) is local-first search

中文介绍 介绍zg（zvec-grep）作为本地搜索工具，解决人类和代理在大量本地文件中查找信息的问题。

Proactive cyber defense for governments and enterprises

DeepMind Blog · 09/03 00:24

中文介绍 DeepMind发布政府和企业主动网络安全防御方案。

Introducing Gemini 3.8 Flash and 3.8 Flash Cyber

DeepMind Blog · 09/03 00:18

中文介绍 DeepMind推出Gemini 3.8 Flash和3.8 Flash Cyber。

Facilitating AI integration with simplicity at scale

MIT Tech Review AI · 09/02 22:00

As companies scale, the technology supporting operations can become a liability just as quickly as it becomes an asset. Disconnected systems, site-specific tools, spreadsheets, and manual workarounds can create data silos that make it harder to spot problems early, coordinate responses, and make dec

中文介绍 文章讨论公司规模扩大时，如何简化AI集成，避免技术成为负担。

Real-Time Intelligence with IBM Time Series Models on Confluent

Hugging Face Blog · 09/02 21:49

中文介绍 Hugging Face Blog介绍IBM时间序列模型在Confluent上的实时智能应用。

ATV Big Air Tour turned 3 days of work into 3 hours with ChatGPT

OpenAI News · 09/02 20:00

ATV Big Air Tour uses ChatGPT Work to speed up marketing, merchandising, and more. It even turned merchandise photos into an inventory website in 15 minutes.

中文介绍 OpenAI报道ChatGPT如何将ATV Big Air Tour的工作效率提高至原来的1/3。

[AINews] Claude Fable/Mythos 5.1: new SOTA model, 75% cache price cut but 70% more output tokens

Latent Space · 09/02 15:46

Queue the usual rush of model launches...

中文介绍 Claude Fable/Mythos 5.1发布，SOTA模型缓存价格下调75%，输出令牌增加70%。

Fable 5.1 🧠, World Labs Atlas 🌍, Cognition $47B 💰

TLDR AI · 09/02 08:00

中文介绍 TLDR AI报道Fable 5.1和World Labs Atlas项目，Cognition获得47亿美元投资。

BenchMIRT: What are LLM benchmarks actually measuring?

Hugging Face Blog · 09/02 05:39

中文介绍 Hugging Face Blog讨论LLM基准测试的实际测量内容。

Introducing agentic video understanding with Gemini

DeepMind Blog · 09/02 01:08

中文介绍 DeepMind推出Gemini中的代理视频理解功能。

How AI-native companies turn workflows into operating capability

OpenAI News · 09/02 01:00

Basis, Clay, and Exa Labs use AI agents to improve onboarding, account management, and developer integrations. See what enterprise leaders can apply.

中文介绍 OpenAI介绍AI原生公司如何将工作流程转化为运营能力。

PRs NOT Welcome: How Top AI Open Source Projects Are Managing Thousands of Contributors

Latent Space · 09/02 00:17

Vercel’s AI SDK, Astro, Flue and tldraw are replacing drive-by community PRs with software factories, where teams of agents apply fixes and features.

中文介绍 Latent Space探讨顶级AI开源项目如何管理数千名贡献者。

Path to Astra: critical capabilities and frontier safeguards

OpenAI News · 09/01 21:00

Astra is the first OpenAI model to meet the Critical cybersecurity capability threshold under the Preparedness Framework, with stronger safeguards for release.

中文介绍 OpenAI的Astra模型满足关键网络安全能力阈值，具备更强大的安全防护。

Healthcare organizations can now connect EHR and additional industry data to ChatGPT

OpenAI News · 09/01 20:00

ChatGPT can now connect to trusted healthcare data, helping clinicians securely access patient context, medical research, and more.

中文介绍 ChatGPT现在可以连接到可靠的医疗数据，帮助临床医生安全访问患者信息。

Claude Fable 5.1 and Claude Mythos 5.1

Smol AI News · 09/01 13:44

**Anthropic** released **Claude Fable 5.1** and **Claude Mythos 5.1**, which share base weights but differ in safeguards and routing, showing improved coding performance and usability with a **75% cache-read price cut to $0.25/MTok**. Benchmarks highlight strong coding/science results, though Fable

中文介绍 Anthropic发布Claude Fable 5.1和Claude Mythos 5.1，基准测试显示编码和科学能力增强。

[AINews] Fal’s H3 Max Live breaks the infinite videogen barrier

Latent Space · 09/01 12:36

You can now create decent video faster than you watch it. This is the start of... something. We’re not sure what.

中文介绍 Fal’s H3 Max Live突破无限视频生成障碍，视频生成速度超过观看速度。