2026-09-05

DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

👍 17

09/03 08:00

Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work in the outcome-blind setting, where ground-truth success signals are not available. Multi-criteria rubrics are a popular way to supply such a rewar

Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs

👍 9

09/03 08:00

Long-video language models cannot look at every frame: an hour sampled once per second is 3,600 images, and a system keeps only a small fixed slice of that pool. Which frames survive that slice is usually treated as a preprocessing detail; we test whether it should be. Published selectors make the c

Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction

👍 33

09/03 08:00

Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed first-frame anchor forces extrapolation far beyond the training distribution. Small drifts accumulate and amplify into significant geometric collapse. However, we observe that per

PACE: Towards Surfacing Hidden Conflicts in User Requests

👍 16

09/03 08:00

Personalized assistants should not only comply with user requests but also assess whether those requests are appropriate given the user's current circumstances. However, prior work has primarily focused on accurately executing requests, overlooking the need for assistants to account for context and

Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding

👍 22

09/03 08:00

Streaming video understanding requires multimodal large language models (MLLMs) to process continuous visual inputs and respond to user queries under strict causality and bounded memory. Existing approaches typically compress historical observations into an external memory bank and retrieve query-re

WorldReward: Reward Modeling for Camera-Conditioned World Models

👍 15

09/03 08:00

Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected scene changes while appearance, geometry, and temporal dynamics remain coherent. Existing rewards assess these requirements separately: geometry-based rewards estimate trajectory executi

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

👍 123

09/03 08:00

Large language models achieve superior performance on tasks that require extended reasoning, but long chains of thought make the KV cache a severe memory bottleneck. Existing KV cache compression methods share one paradigm: score each cached token by some estimate of how much it will matter later, a

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

👍 64

09/03 08:00

On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. Existing work has mainly studied its algorithmic behavior, leaving the role of training data unclear. We examine this role at the data-minimal limit by training on a single query. One-

CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation

👍 18

09/03 08:00

MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish scenes containing the same concepts but different attribute-object bindings. Yet the same backbone can resolve such distinctions when used as a cross-attentive reranker, motivating us to distill its c

Editable Visual Design

👍 32

09/03 08:00

While diffusion base models such as GPT-Image-2 and Nano-Banana exhibit remarkable visual expressiveness, their end-to-end generation inherently yields flattened bitmaps with error-prone text, precluding layer-wise post-editing. Conversely, code-based visual generation via Coding Agents provides pre

Environment Evolution for Terminal Agents

👍 10

09/03 08:00

Scaling interactive and verifiable environments is critical for training terminal agents. As frontier models become more capable, environments synthesized from scratch become less challenging and thus provide limited learning signals. Recent co-evolution methods iteratively synthesize environments n

Principia: Relational Physics Tests for Video Models

👍 10

09/03 08:00

Evaluating physical reasoning in video models is difficult because absolute motion measurements depend on frame rate, object scale, and camera calibration, all of which are often ambiguous or unavailable in generated video. We propose a different approach. When two objects in the same scene obey the

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

👍 213

09/03 08:00

As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what agent post-training actually requires: each can be re-queried into many verifiable tasks and provides execution feedbac

Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM

👍 66

09/03 08:00

Hybrid LLMs pair softmax attention with linear-attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the context in fixed size. Early community 4-bit quantizations of Qwen3.8-27B (48 GDN layers, 16 attention layers) left the GDN block in 8- or 16-bit precision -- especially

VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement

👍 2

09/02 08:00

Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of indicating the obligation a clip violates or the moment it fails. We present VeriPhy, an auditable physical-verification system in which a text-only planner compiles the prompt int

Debias-SparseGPT: Bias-Aware Pruning for Large Language Models

👍 2

09/02 08:00

Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of Large Language Models (LLMs). However, recent studies show that weight sparsification methods, such as SparseGPT, can amplify existing biases in models, with outputs varying signific

Exploring Collaboration between a language and a non-language agent

👍 5

09/02 08:00

LLMs are increasingly deployed as orchestrators that coordinate specialized subagents to solve complex tasks through natural language. However, in many important domains like game playing and robotics, the strongest available agents are not language models. Integrating non-language agents with LLMs

Replacing Training with Memory: Listwise Selection for Text-to-SQL

👍 2

09/01 08:00

Modern Text-to-SQL systems often follow generate-execute-select pipelines, generating multiple candidate queries then selecting the best one. Listwise selection, by jointly comparing multiple candidates, has been widely adopted, but fine-tuning listwise selectors is costly. We thus propose a fine-tu

Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens

👍 2

09/01 08:00

A language model's prediction of its next token develops across layers, and lens methods track this process by decoding intermediate hidden states into tokens. But a lens reading reflects both the hidden state and the readout (the unembedding matrix) used to decode it. Many lenses are fit on a corpu

Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models

👍 3

09/01 08:00

Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether this reflects an internal representation of 2D spatial layout or simply the ability to translate spatial descriptions into code. We introduce Autor

Using Grounded Theory for Agent Behavior Analysis at Scale

👍 12

08/31 08:00

Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in long, often unfamiliar tasks where pre-built classifiers fall short. We propose to bring grounded theory into agent trajectory analysis: a six-decade-old qualitative method from the soci

RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests

👍 16

08/31 08:00

Coding agents are now commonly evaluated on the SWE-bench family of benchmarks, whose tasks are built from curated GitHub issues: long, structured, and information-rich. Real user requests, however, are typically far shorter and less structured. To characterize this gap, we define a six-category inf

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

👍 29

08/31 08:00

Agent performance depends jointly on the model parameters and the executable harness code that manages context and control flow. Optimizing either component in isolation can leave the system bottlenecked by its frozen counterpart: weight updates can change which harness is effective, while harness u

FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos

👍 3

08/31 08:00

We present FoldingAgent, an agentic framework for inferring explicit parametric folding programs directly from origami demonstration videos. Our framework leverages the reasoning power of a pre-trained Vision-Language Model (VLM) equipped with a suite of specialized tools that enable the agent to si

Ignorance or Incompetence? Constructing Knowledge-Gated, Verifiable Tasks for LLM Agents

👍 4

08/31 08:00

Professional agent tasks often depend on conventions that are absent from public corpora, yet benchmarks rarely control whether an agent has access to those conventions. We introduce a knowledge-gated task-construction protocol that separates a task instruction from a compact artefact containing pri

Small Language Models as Judges for Rubric-Based Reinforcement Learning

👍 1

08/30 08:00

Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring responses against instance-specific criteria. However, this makes reward computation expensive: training requires repeated rubric judging, often with proprietary APIs or local generative

Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space

👍 2

08/29 08:00

Reinforcement learning with verifiable rewards (RLVR) substantially improves single-sample accuracy (pass@1) but causes the policy's solution space to contract, diminishing the returns of test-time scaling. In this work, we investigate where inside a reasoning trajectory this breadth is lost: does t

QCell: Recombining and Aligning Cell Queries for Overlapping Instance Segmentation

👍 7

08/29 08:00

Instance segmentation of overlapping cells in microscopy remains challenging due to semi-transparent structures that produce weak boundaries and mixed visual evidence in overlap regions. Existing methods address this through local regions of interest or shape priors but lack global reasoning across

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

👍 139

08/27 08:00

Large language models offer broad capabilities, but adapting them to evolving domains, tools, and requirements often entails repeated post-training. Autonomous systems automate parts of this process by proposing updates, training candidates, and using evaluation feedback to select subsequent proposa

Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering

👍 26

08/19 08:00

Knowledge-Based Visual Question Answering (KB-VQA) relies on retrieving external information to answer queries involving long-tail entities. However, existing retrieval pipelines predominantly employ CLIP-style dual encoders, which prioritize surface-level visual similarity over entity-level semanti

The Cognitive Revolution (When Machines Do The Thinking)

@Konstantine · 17.6K 粉丝 · 256.2K 阅 · 529 赞 · 100 转

09/02 23:07

We externalized our muscles and built the modern world. Now we are externalizing our minds. Most mornings I ride to work in a Waymo. The car is doing physical work: five thousand pounds of metal and

中文介绍 Konstantine探讨认知革命，从肌肉到思维的机械化，并以Waymo为例阐述AI在现实生活中的应用。

CarryGo, here we go!

@CarryGo_AI · 9 粉丝 · 192.8K 阅 · 1.0K 赞 · 2 转

09/04 18:34

Inside CarryGo lies a world model—helping organizations see, simulate, act and learn as a system. At the product level, CarryGo is a world model, built first for business. At the system level, it is

中文介绍 CarryGo AI发布，介绍其世界模型如何帮助企业和系统层面上的决策与学习。

Prediction: AI will collapse

@wordgrammer · 26.1K 粉丝 · 120.8K 阅 · 602 赞 · 33 转

09/03 05:30

The dot com bubble got some things right. It noticed that the internet was going to be big. It noticed that the value generated by the internet would roughly scale in proportion with the amount of

中文介绍 wordgrammer预测AI可能面临类似互联网泡沫的危机，强调互联网价值与规模的关系。

How to design a Brand System from 1 reference image

@AmirMushich · 80.6K 粉丝 · 102.2K 阅 · 501 赞 · 42 转

09/03 00:11

For 10+ years, I've been creating branding & ads for Warner Music, PepsiCo, and others. Now I combine that experience with AI to build hi-end visual systems faster. This article shows my complete

中文介绍 AmirMushich分享从单一图像设计品牌系统的经验，结合AI技术加速高端视觉系统构建。

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 irabukht推荐7个Grok Bots营销机器人，提供广告、SEO和GEO的提示词和营销策略。

AI Engineering Skills Map: Using coding agents

@AndrewYNg · 1.9M 粉丝 · 48.9K 阅 · 918 赞 · 136 转

09/04 23:02

A key AI engineering skill is using coding agents. Your skill at steering them both to write code and to carry out non-code tasks, such as analyzing data or managing system operations, allows you to

中文介绍 AndrewYNg讨论AI工程技能，重点介绍使用编码代理进行代码编写和非代码任务的技巧。

Grok Bot for Work

@joshkim · 8.3K 粉丝 · 42.4K 阅 · 525 赞 · 41 转

09/04 06:03

I can't do my job without Grok Bot. It happened really quickly. A few weeks ago, I wasn’t leveraging agents like the AI-pilled experts you see on X and LinkedIn. I was still a human in the loop:

中文介绍 joshkim分享Grok Bot在日常工作中的重要性，从依赖人工转向依赖AI代理。

Codex has changed my life as a solopreneur

@jonnym1ller · 20.7K 粉丝 · 36.0K 阅 · 510 赞 · 23 转

09/04 06:53

It's difficult to exaggerate how absurdly life-changing Codex has been for me as a solopreneur in recent months. And yet people have been saying 'but what do you actually use it for' (so I decided to

中文介绍 jonnym1ller评价Codex对他作为自由职业者的生活影响，并分享实际应用场景。

Introducing Gemini 3.8 Flash and 3.8 Flash Cyber

@GoogleAIStudio · 198.5K 粉丝 · 26.2K 阅 · 507 赞 · 59 转

09/03 00:48

Our newest Gemini models deliver next-generation intelligence for agentic workflows and cybersecurity. Building on the momentum of 3.7 Flash from three weeks ago and marking our third Flash release in

中文介绍 GoogleAIStudio介绍Gemini 3.8 Flash和3.8 Flash Cyber模型，为工作流和网络安全提供下一代智能。

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 QwenDevs介绍zg（zvec-grep）本地搜索工具，帮助快速准确地定位大量本地文件中的信息。

Architecting memory and storage in the AI era

MIT Tech Review AI · 09/05 02:39

The era of AI inference has arrived. Imagine a healthcare system analyzing millions of data points in real time to accelerate life-saving medical research, or an intelligent assistant instantly resolving thousands of complex customer needs at once. These real-world breakthroughs rely on advanced inf

中文介绍 AI推理时代来临，医疗系统可实时分析百万数据点，智能助手可即时解决数千个复杂客户需求。

Data from drones in Ukraine is fueling a new Wild West marketplace

MIT Tech Review AI · 09/04 17:25

Battlefields in Ukraine are littered with the remnants of drones, which are now firmly established as a critical weapon of modern warfare. But behind all that wreckage, there’s a new gold mine for the defense sector. The data drones generate will far outlast the wars in which they are used to fight,

中文介绍 乌克兰战场上的无人机残骸成为新的金矿，为国防部门提供大量数据。

[AINews] GPT-6 Astra: OpenAI’s biggest LLM launch of all time

Latent Space · 09/04 13:18

new SOTA computer use and coding, 2.5x pricier per token, but WAY cheaper per task, less monitorable. overall, a very successful launch of OpenAI’s new frontier model class.

中文介绍 OpenAI发布GPT-6 Astra，价格每令牌高出2.5倍，但任务成本更低。

GPT-6 Astra 🚀, Grok Bot Enterprise 🤖, Runway world model 🌎

TLDR AI · 09/04 08:00

中文介绍 OpenAI推出GPT-6 Astra、Grok Bot Enterprise和Runway world model。

GPT-6 Astra: an automated AI Engineer you can hire for <$6 an hour

Latent Space · 09/04 05:09

We spent 20B+ tokens of GPT-6 Astra to explore everything. Here’s our learnings.

中文介绍 GPT-6 Astra以每小时低于6美元的价格提供自动化AI工程师服务。

Introducing WeatherNext 3, our most advanced and accurate global weather AI model

DeepMind Blog · 09/03 23:02

中文介绍 DeepMind推出WeatherNext 3，最先进和准确的全球天气AI模型。

Daybreak for Frontline Defenders: $1B to protect essential services

OpenAI News · 09/03 21:15

OpenAI introduces Daybreak for Frontline Defenders. A $1 billion commitment expands access to frontier cyber AI, training, and support for essential services.

中文介绍 OpenAI投资10亿美元支持前线卫士，扩大关键服务的网络AI、培训和支援。

NeoMME: an efficient Multimodal-native and Multilingual Encoder

Hugging Face Blog · 09/03 21:13

中文介绍 Hugging Face推出NeoMME，一个高效的多模态和双语编码器。

Playco cut manual fixes 50% prototyping games with GPT-6 Astra

OpenAI News · 09/03 20:00

Using GPT-6 Astra, Playco built three themed game prototypes from one grey box foundation and reported 50% fewer manual fixes than with the previous model.

中文介绍 Playco使用GPT-6 Astra将游戏原型制作时间缩短50%。

Legora reviewed 41 documents in minutes with GPT-6 Astra

OpenAI News · 09/03 20:00

Legora used GPT-6 Astra to review 41 documents in minutes, find all four planted errors, and improve performance by nearly 40% in this financial-review workflow.

中文介绍 Legora使用GPT-6 Astra在数分钟内审查41份文件，发现所有四处植入的错误，并将性能提高近40%。

[AINews] Muse Spark 1.3 matches GPT-5.6-Sol, confirming Meta Superintelligence as the newest Frontier Lab, >90% discount for training

Latent Space · 09/03 12:38

an epic comeback story for Meta

中文介绍 Muse Spark 1.3与GPT-5.6-Sol相匹配，确认Meta超级智能为最新前沿实验室，训练费用折扣超过90%。

Safety overview: GPT-6 Astra

OpenAI News · 09/03 08:00

GPT-6 Astra is our most capable broadly deployed model and our first to reach the Critical level of cybersecurity capability under our Preparedness Framework.

中文介绍 GPT-6 Astra是我们最广泛部署的模型，首次达到关键级别的网络安全能力。

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

Hugging Face Blog · 09/03 08:00

中文介绍 通过100步GRPO微调350M模型，以实现更好的结构化输出。

Give Your Coding Agents a Memory You Own

Hugging Face Blog · 09/03 08:00

中文介绍 为您的编码代理提供您自己的记忆。

Training a coding model to paint watercolours with TRL and OpenEnv

Hugging Face Blog · 09/03 08:00

中文介绍 使用TRL和OpenEnv训练编码模型以绘制水彩画。