2026-09-07

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

👍 24

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

👍 15

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

👍 46

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

👍 22

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

👍 29

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

👍 23

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

👍 163

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

👍 78

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

👍 24

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

👍 42

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

👍 17

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

👍 16

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

👍 272

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

👍 74

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

👍 12

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

👍 3

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

👍 3

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

👍 3

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

👍 4

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

👍 18

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

👍 26

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

👍 30

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

👍 4

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

👍 2

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

👍 10

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

👍 14

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

👍 150

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

Grok Imagine Odyssey Contest Winners

@imagine · 79.2K 粉丝 · 714.5K 阅 · 532 赞 · 86 转

09/05 04:49

Homer had a lyre. You had Grok Imagine. Thousands of you quoted our launch post and built original Odyssey scenes in Grok Imagine. Image, video, and the voices. Three to five minutes, with at least

中文介绍 Grok Imagine Odyssey Contest揭晓获奖作品，用户用Grok Imagine构建原创奥德赛场景，展现图像、视频和声音。

Five things I learned from using Astra

@dkundel · 23.9K 粉丝 · 225.2K 阅 · 520 赞 · 44 转

09/05 04:27

Back in February, getting Codex to build LEGO models took a custom skill, complicated instructions, and hours of iteration. And it was still not great. I came away thinking it wasn’t something models

中文介绍 作者分享使用Astra的经验，指出之前用Codex制作乐高模型需要复杂指令和迭代，效果不佳。

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产品介绍，一个世界模型，帮助组织系统性地观察、模拟、行动和学习。

Applied AI Doesn't Work

@vasuman · 96.1K 粉丝 · 109.9K 阅 · 517 赞 · 32 转

09/05 06:17

The world has spent a fortune on AI. For most enterprises, nothing changed. I've spoken to over 300 CEOs, CIOs and CFOs at the largest companies on Earth. I learned most companies apply AI onto their

中文介绍 作者指出企业应用AI的困境，尽管投入巨资，但对多数企业来说，情况并未改变。

SARVAM AI Interview Experience and Prep - Backend Engineer (On-Device AI) Internship:

@buzzy_bit · 767 粉丝 · 97.5K 阅 · 500 赞 · 20 转

09/05 15:30

Disclaimer: This post is written purely to share my experience and the way I prepared. It is not a leaked question bank, I'm intentionally not reproducing exact interview questions, and I'm not naming

中文介绍 分享SARVAM AI面试经验，不涉及具体面试问题，仅为分享准备过程。

How I make content with Astra

@nickbaumann_ · 20.0K 粉丝 · 74.8K 阅 · 511 赞 · 38 转

09/05 04:37

I've been using Astra in Codex to edit videos we've shipped on the official ChatGPT Instagram. I've also been using it to pull clips from longer videos and create product animations. And what's really

中文介绍 作者介绍使用Astra在Codex编辑视频，创建产品动画的经验。

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 介绍AI工程技能，特别是使用编码代理进行非代码任务的能力。

Rethinking skills and prompts for GPT-6 Astra

@pvncher · 35.4K 粉丝 · 44.6K 阅 · 508 赞 · 37 转

09/05 05:44

Coding agents have come a long way, and best practices are changing fast. What used to require a lot of handholding and scaffolding no longer does. If you’ve been using agents in your projects over

中文介绍 讨论使用编码代理的最佳实践，指出过去需要大量手动引导的做法已不再适用。

An Alien Mind

OpenAI News · 09/06 17:00

Jakub Pachocki reflects on increasingly capable AI and the challenge of keeping it aligned. He calls for stronger safeguards and international coordination.

中文介绍 Jakub Pachocki强调加强AI安全和国际协调，以应对AI能力提升的挑战。

Research acceleration: The view inside OpenAI

OpenAI News · 09/06 16:00

Inside OpenAI, coding agents are reshaping AI research. Explore early data on agent usage, experiment velocity, task complexity, and research acceleration.

中文介绍 OpenAI内部，编码智能体正在重塑AI研究，加速研究进展。

OpenClaw Power, MacBook Simplicity: Five Days With Grok Bot

Latent Space · 09/05 23:01

SpaceXAI’s Grok Bot has the same level of programming power as OpenClaw, but it’s programmable at a different level of abstraction.

中文介绍 SpaceXAI的Grok Bot编程能力与OpenClaw相当，但编程抽象级别不同。

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，实时分析海量数据，加速医疗研究。

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国防行业的新金矿，数据价值巨大。

[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，这是其最大的LLM发布，具有更高的性价比。

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

TLDR AI · 09/04 08:00

中文介绍 OpenAI发布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花费20B+ tokens进行探索，带来宝贵经验。

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，扩大关键服务的前沿网络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多语言编码器。

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利用GPT-6 Astra在数分钟内审查41份文件，性能提升近40%。

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构建游戏原型，减少50%手动修正。

GPT-6 Astra: A new generation of intelligence

OpenAI News · 09/03 19:00

Introducing GPT-6 Astra, our most intelligent and aligned model yet, with state-of-the-art capabilities across computer use, coding, cybersecurity, and science.

中文介绍 OpenAI推出GPT-6 Astra，新一代智能模型，具备多领域先进能力。

[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 Meta的Muse Spark 1.3匹配GPT-5.6-Sol，Meta超智能成为最新前沿实验室。