2026-10-08

AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model

👍 6

10/07 01:56

Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's goal. The agent cannot simply ignore the page, because the page also holds the values and controls the task requires. Current def

CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?

👍 52

10/06 08:00

Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and refine the checker through repeated compilation and analysis feedback. Existing coding-agent benchmarks focus on tasks such as patch generation or vulne

Sherpa: Teaching LLMs to Teach Adaptively

👍 6

10/06 08:00

Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is not the same as being able to teach it. Existing approaches to training LLMs as teachers rely on demonstrations, preference data, or predefined pedagogical criteria that specify what g

A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies

👍 4

10/06 08:00

A safe action is not necessarily a viable one. A frozen vision-language-action (VLA) policy can favor a locally admissible move that leaves no policy-supported route to safe task completion. We call this the feasibility-likelihood gap: likelihood ranks the next move, while feasibility depends on the

DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks

👍 9

10/06 08:00

LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool behaviors or environment conventions on their own. Without memory of past attempts, they repeat the same mistakes across tasks, leading to more task failures and longer trajectori

UNREAL: Unifying Retrieval and Long-Context with a Single Model

👍 19

10/06 08:00

Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-internal mechanism can select evidence across this range. We introduce UNifying REtrieval And Long-Contex

NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale

👍 10

10/06 08:00

Agentic reinforcement learning (RL) disaggregates training from rollout, so each policy update must reach the rollout clusters before the next batch. Transferring a full 1T checkpoint for such weight synchronization (refit) takes 87.5 min between two AWS regions. Measurements of BF16 training show t

Towards In-Parameter Memory Augmentation for Large Language Models

👍 5

10/06 08:00

Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context learning (ICL) and ICL-based agent harness remain flexible, but they consume conte

From Evidence to Action: How Tool-Using Agents Fail

👍 34

10/06 08:00

Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand. We study where this evidence-to-action chain breaks as agents move from deciding whether to act to executing single actions and

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

👍 153

10/06 08:00

On-Policy Distillation (OPD) trains a student on its own generations using teacher feedback. With different tokenizers, comparing teacher and student predictions requires alignment at both sequence and vocabulary levels. In this paper, we examine whether expanding this alignment coverage improves le

Stepped MoE: Segment-Level Routing with Configurable Inference Complexity

👍 2

10/05 08:00

Training large language models (LLMs) is resource-intensive, and adapting them for diverse deployment scenarios with varying computational constraints remains challenging. While elastic architectures enable flexible model deployment and sparsely activated models allow input-adaptive computation, exi

Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding

👍 11

10/05 08:00

On-policy reinforcement learning has become a central paradigm for improving the reasoning abilities of large language models. However, its effectiveness is often limited by reward sparsity: when a model fails to discover correct trajectories for difficult problems, the optimization process receives

Conditional Trajectory Peaks: Single-Pass Multimodal Policies over Action Chunks

👍 1

10/05 08:00

Multimodal imitation learning requires diverse executable futures under the same observation and consistent behavior across replanning cycles. We present Conditional Trajectory Peaks (CTP), a single-pass policy framework that jointly predicts complete action-chunk candidates, probability masses, and

Execution-Aligned Progressive Noise for Consistent Asynchronous Replanning in Generative Robot Policies

👍 1

10/05 08:00

Continuous asynchronous replanning is essential for real-time generative robot policies, but independent stochastic initialization can cause mode switching and inconsistent continuation across action chunks. We propose Execution-Aligned Progressive Noise (EAPN), which introduces structured stochasti

Learning to Read the Contextual Tokens in Diffusion Transformers

👍 6

10/05 08:00

Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens through multimodal attention, forming dynamic contextual tokens whose function is not well understood. In this work, we introduce a fra

HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing

👍 5

10/05 08:00

Linear attention enables efficient long-context autoregressive decoding by compressing history into recurrent states, but this compression can make selective access to sparse and distant information difficult. Existing chunk-based extensions increase memory capacity, yet learned chunk-mixing coeffic

MiniCorp: The Last Mile of the AI Agent Firm

👍 15

10/05 08:00

The last mile toward enterprise AGI is a company that runs itself. Training and adapting such agents require longitudinal enterprise data, which remain scarce, costly to acquire, and often restricted by privacy constraints. Historical archives are also frequently incomplete and record only what actu

DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation

👍 12

10/03 08:00

On-policy distillation (OPD) has emerged as a widely used paradigm for post-training large language models, reducing the train--test mismatch of conventional distillation by supervising the student on its own generated trajectories. However, existing OPD objectives remain largely token-local and out

Magic-W0: A Structured World-Action Foundation Model for Physical Intelligence

👍 1

10/03 08:00

World-action models (WAMs) augment robot policies with action-conditioned environment dynamics, yet existing approaches largely rely on future observation reconstruction or generic latent prediction and lack structured, control-oriented world representations tightly coupled with action generation. W

ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution

👍 1

10/03 08:00

Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful concepts, limiting their interpretability and trustworthiness. We introduce Concept-based Explanations (ConEx), a novel framework that bridges saliency v

Cross-Lingual Alignment for Decoder-Only Models using MoE Routers

👍 1

10/02 08:00

Cross-lingual contrastive learning has been a core component of multilingual encoder training, but the ability to explicitly align representations is not possible in decoder-only LLMs because of varying multilingual tokenization. However, a growing amount of research suggests that even in LLMs, high

Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale

👍 3

10/02 08:00

A trainable input embedding table assigns each vocabulary item an independently adjustable vector. We investigate whether this token-specific parameterization is required for substantial language-modeling capability, or whether a shared Transformer can learn from fixed token identities. We compare t

Harness-Aware Distillation for Small Language Model Agents

👍 5

10/02 08:00

Language model agents are deployed with a harness, the software around the model that manages its context, tools, and feedback. When such an agent is distilled into a smaller one, the harness stays in place, so the student mainly needs the teacher-specific abilities that the harness cannot provide,

AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation

👍 16

10/01 08:00

Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version. The evidence is incomplete and the metrics come from fallible LLM judges. We report on AGO AI Quality Gate (AGO), an evidence-first quality-gate framework depl

Learning Functional Subspaces for Neural Network Compression

👍 3

09/30 08:00

Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping the matrices dense, and thus efficient on standard hardware. Existing methods, however, choose the subspace to remove from each weight matrix with lo

Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing

👍 24

09/29 08:00

Vision-language-action (VLA) policies often fail when a robot's executed motion deviates from their commanded action. Such execution errors arise from the robot's mechanics and operating conditions, such as wear and payload changes. We propose self-compensating VLA, a deployment-time adaptation meth

Multilinguality in Hybrid Attention LLMs

👍 3

09/28 08:00

In response to the growing demand for long sequences in agentic and reasoning use cases, many state-of-the-art LLMs combine multiple variants of attention to mitigate the quadratic complexity of traditional softmax attention. These hybrid attention LLMs aim to balance the strengths and limitations o

SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving

👍 10

09/28 08:00

Mixture-of-experts (MoE) models activate few experts per token, yet batched decoding can access nearly the entire expert pool, making expert-weight traffic a major bottleneck. Expert pruning reduces this traffic, but conventional approaches also prune compute-bound prefill, sacrificing model quality

Adaptive Latent Capacity for World Models

👍 10

09/26 08:00

We introduce Adaptive LeWorldModel (ALeWM), a world model based on a joint-embedding predictive architecture (JEPA) that learns to concentrate predictive information in compact prefixes of a wide latent representation. To encourage this ordering, ALeWM learns a sequence-conditioned distribution over

Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning

👍 4

09/24 08:00

In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech. We propose accent analogy guidance (AAG), a training-free sampler term that subtracts an accent direction estimated from the model's own predictions for one synthetic voice rendered in both languages

He Who Controls the Compute Controls the Universe

@stevenmarkryan · 458.8K 粉丝 · 124.9K 阅 · 541 赞 · 84 转

10/05 13:25

Incredible things are happening in AI. What’s more incredible is that it’s still EXTREMELY early. As in, Day 0.000. Things are only going to get crazier from here. In case you’ve been living under a

中文介绍 博主探讨AI发展现状，认为目前仍处于非常初级的阶段，未来将更加疯狂。

Every language learner gets a tutor now

@TryLiveAvatar · 1.1K 粉丝 · 123.4K 阅 · 692 赞 · 188 转

10/06 02:45

The best way to learn a language was always a patient tutor. For the first time, everyone can have one. Here's what that changes for learners, teachers and schools. The hardest part is speaking Ask

中文介绍 博主介绍语言学习AI助手，强调其对学生、教师和学校带来的变革。

AI won't take your job anytime soon. In 10 yrs, only 5% of what humans do will be replaced by AI

@mustafasuleyman · 1.2M 粉丝 · 99.2K 阅 · 587 赞 · 104 转

10/06 22:16

This is the prediction Nobel laureate Daron Acemoglu makes in the first issue of The Humanist Review, our new magazine exploring the future of AI, published by MAI. He argues we need to stop

中文介绍 博主分享诺贝尔奖得主Daron Acemoglu的预测，未来10年内AI将取代人类工作的比例仅为5%。

If you have too many interests, build this AI system in 1 hour

@Hesamation · 90.6K 粉丝 · 21.4K 阅 · 618 赞 · 51 转

10/06 17:46

if you have an ADHD brain, you probably have six different goals, you get overwhelmed, and you miss days without working on any one of them. that's me. I love agents, harnesses, RL, LLM architecture,

中文介绍 博主分享针对多兴趣人士的AI系统构建方法，利用代理、 harnesses、RL和LLM架构实现高效目标管理。

Multimodal open d1 decision models for the edge

Hugging Face Blog · 10/08 00:54

中文介绍 Hugging Face推出边缘多模态开放决策模型d1。

Can a Cloud-Native Harness Make Agents Reliable Beyond the Desktop?

Latent Space · 10/07 22:10

Kubernetes co-creators Craig McLuckie and Joe Beda aim to bring agent harnesses fully into the cloud.

中文介绍 Kubernetes共同创始人Craig McLuckie和Joe Beda计划将代理工具完全带入云端。

One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO

Hugging Face Blog · 10/07 20:45

中文介绍 Hugging Face推出Nemotron模型，在IOI和IMO比赛中获得金牌。

Helping teens learn, plan, and shape the future of AI

OpenAI News · 10/07 20:00

College Planner is coming to ChatGPT for Teens to help students manage college applications, alongside new flashcards, quizzes, and a teen AI council.

中文介绍 OpenAI将为青少年推出College Planner插件，帮助他们管理大学申请。

Radisson Hotel Group brings hotel discovery into ChatGPT

OpenAI News · 10/07 15:00

Radisson partnered with Accenture to build a ChatGPT plugin using OpenAI technology, helping travelers find, compare, and book hotels while planning their trips.

中文介绍 Radisson酒店集团与Accenture合作，在ChatGPT中推出酒店发现插件。

[AINews] Quasi-Riemann-Hypothesis: OpenAI publishes 722 math papers solving 90 of the top 500 open math problems; “the most significant moment” in >100 years of mathematics

Latent Space · 10/07 12:55

Our head hurts.

中文介绍 OpenAI发布722篇数学论文，解决90个顶级开放数学问题。

GPT-6 and Intelligent UI for everyone

OpenAI News · 10/07 08:00

GPT‑6 is rolling out globally in ChatGPT with Intelligent UI, delivering faster responses with visuals and interactive experiences you can explore and use directly.

中文介绍 OpenAI在全球范围内推出GPT-6，配备智能UI，提供更快的视觉交互体验。

Mistral Large 4 🧠, OpenAI Decisions API ❓, Nano Banana 2.1 🍌

TLDR AI · 10/07 08:00

中文介绍 OpenAI发布Mistral Large 4模型，并推出Decisions API。

Atlassian and OpenAI expand partnership to turn enterprise knowledge into action

OpenAI News · 10/07 00:00

Atlassian and OpenAI are expanding their partnership to connect frontier models with enterprise knowledge and help teams plan, build, and deliver work.

中文介绍 Atlassian和OpenAI扩大合作，将前沿模型与企业知识连接。

How Jump Trading is scaling quant research with ChatGPT

OpenAI News · 10/06 20:00

Jump Trading uses OpenAI to expand quantitative research. See how longer-running AI workflows combine multiple data sources with human review.

中文介绍 Jump Trading使用OpenAI扩展量化研究，结合多数据源和人工审核。

Sharing AI progress in mathematics

OpenAI News · 10/06 20:00

OpenAI publishes new results on open problems in mathematics from an internal frontier model and shares Lean proof formalizations and research details on GitHub.

中文介绍 OpenAI发布关于数学开放问题的内部前沿模型新结果。

Advancing computer use with Ironclad

OpenAI News · 10/06 18:00

Learn how OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows to advance computer use for professional work.

中文介绍 OpenAI与Ironclad合作，训练和评估AI代理在复杂合同流程中的应用。

[AINews] Reflection Beam - 501B-A23B American Open Model

Latent Space · 10/06 14:28

A small win for US open source

中文介绍 美国开源项目Reflection Beam - 501B-A23B取得小胜利。

Instinct group chats 💬, Reflection’s 501B model 🧠, OpenAI text watermarks 🏷️

TLDR AI · 10/06 08:00

中文介绍 Instinct群聊、Reflection的501B模型、OpenAI文本水印。

Connecting AI agents to enterprise knowledge

MIT Tech Review AI · 10/05 23:47

For all the data that AI systems continually amass and analyze, enterprise AI agents often suffer from a curious shortcoming: a lack of knowledge. More than data, knowledge is the understanding of what the data means in the context of individual organizations. AI agents need this understanding to re

中文介绍 企业AI代理缺乏知识，需要理解数据在组织中的意义。