2026-09-23

ACLArena: Agent Continue Learning in Multi-stage Post-training

👍 6

09/21 08:00

Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of training. Yet there is currently no well-established recipe for Agent Continual Learning (ACL), with little understanding of the trade-offs among exist

EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation

👍 1

09/21 08:00

Tool-calling LLM agents are increasingly deployed in enterprise applications. However, effective evaluation and optimization require high-quality, diverse task datasets that are often difficult to obtain due to privacy and other constraints. Existing synthetic task generation methods often produce g

Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention

👍 4

09/21 08:00

Linear RNNs based on the delta-rule enable efficient sequence modeling, but their linear updates with a low-rank correction constrain their expressivity. Prior work has shown that composing two delta-rule transitions in a single recurrent update can model a 2D rotation, but this increases the rank a

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

👍 48

09/21 08:00

Retrieval-Augmented Generation (RAG) systems over enterprise knowledge bases must ingest heterogeneous document formats -- PDFs, Word documents, presentations, and scans -- whose content is locked inside complex visual layouts, multi-column pages, and dense tables. Rule-based extraction and OCR dest

CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies

👍 11

09/21 08:00

Vision-Language-Action (VLA) policies achieve strong performance in robotic manipulation but remain brittle once execution deviates from nominal trajectories. We propose CARE (Corrective Atomic Robotic Execution), a framework that improves recovery by learning from failures encountered during execut

1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation

👍 7

09/21 08:00

Sparse on-policy distillation (OPD) allocates teacher supervision to a small subset of tokens in student-generated trajectories. However, useful teacher guidance can yield a noisy update when its gradient is estimated from a sampled next token. We study this estimation problem at a fixed prefix in i

onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

👍 27

09/21 08:00

We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as its core interaction: while reading a model response, the annotator locates the first inappropriate token and either picks a substitute from the mode

Harness-Zero: Harness Distillation via Agent-as-Harness

👍 12

09/21 08:00

Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at deployment. Because the best harness varies across domains, instances, and models, a general-purpose agent must either settle f

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

👍 11

09/21 08:00

Agentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs to control how memories are organized, retrieved, and used, placing expensive generation on the critical path of memory operations. We introduce \method, a new agentic memory archit

VideoGen-Agent: Reinforcing Video Generation Agents

👍 35

09/21 08:00

Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to satisfy prompts requiring specialized knowledge, specific identities, physical consistency, or ordered events. In this paper, we present VideoGen-Agent

Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies

👍 5

09/21 08:00

Vision-Language-Action (VLA) models map observations to actions with no objective that accounts for how the world responds, so their robustness is bounded primarily by data coverage. World models carry precisely that missing objective and are better grounded for it, yet rolling the future forward co

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

👍 152

09/21 08:00

An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent ha

Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene

👍 3

09/20 08:00

Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challenge. A central difficulty lies in how object layout is represented. Holistic methods absorb placement into a scene-level generation process, sacrific

Grounded Action Model: 3D Grounding as a Foundation for Robotics

👍 19

09/20 08:00

Manipulation policies must know which objects matter and where they are, yet the pretrained backbones that current robot foundation models build on, from language in vision-language-action models (VLAs) to video generation in world-action models (WAMs), do not directly require this metric grounding,

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents

👍 16

09/20 08:00

Repository-level software engineering (SWE) comprises heterogeneous task categories, whose progress under pooled agentic reinforcement learning can be uneven: gains in some categories coincide with regressions in others, while aggregate resolution obscures these changes. Motivated by this category s

Towards Full Pipeline FP8 Reinforcement Learning for LLMs

👍 3

09/19 08:00

Reinforcement learning (RL) has become a key technique for improving the reasoning and agentic abilities of large language models (LLMs). Although FP8 quantization can accelerate RL training, maintaining stability throughout an FP8 RL pipeline remains challenging. While previous works have focused o

UltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing

👍 1

09/19 08:00

High-quality texture generation is essential for creating realistic and production-ready 3D assets. Recent multi-view diffusion methods have shown promising results for image-guided 3D texturing, but they are typically constrained to low operating resolutions such as 512 or 768, making it difficult

OmniEdu: Open Foundation Models for Learning and Teaching

👍 66

09/19 08:00

Educational foundation models must solve problems, understand curriculum structure, diagnose learner difficulties, and provide appropriate instructional support. Existing educational language models often focus on either problem solving or tutoring, with training mixtures organized by source or task

Transferring the Intelligence of VLMs to Robotic Control

👍 101

09/19 08:00

Humans can seamlessly adapt to both physical and digital worlds, suggesting that while a digital-to-real gap exists in embodiment, environment and task, human intelligence itself may transfer across this gap. This naturally raises a fundamental question: can the intelligence of vision-language model

The Functionalizer: Lossless Functional Decomposition for Subword Tokenization

👍 6

09/18 08:00

Standard subword tokenizers either treat every orthographic variation of a word (such as hello, Hello, HELLO, and Héllo) as unrelated vocabulary entries, which fragments the embedding space, or discard this variation through lossy normalization. We present the Functionalizer, a lossless pre-tokenize

From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention

👍 5

09/18 08:00

A pretrained robot foundation policy may execute most of a long-horizon task yet repeatedly fail at a few critical subtasks. Collecting additional full-task demonstrations for supervised fine-tuning (SFT) requires operators to repeat behaviors the policy already performs well. Reinforcement learning

Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation

👍 1

09/17 08:00

Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents. Exhaustive testing is expensive, so evaluation rests on a sample of labeled units. We treat the evaluation set as a finite population

BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence

👍 15

09/16 08:00

Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tableau. In traditional BI workflows, users need to prepare data by (1) identifying relevant tables, (2) performing data transformations, and (3) building

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

👍 11

09/12 08:00

Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and linguistic cues, while video interaction also requires grounding the conversation in evolving visual context. We present Realtime-Venus, a proactive fu

SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops

👍 3

09/12 08:00

Concurrent local LLM serving on unified-memory desktops must preserve memory headroom and output fidelity, which speed-only rankings overlook. We introduce SiliconBench, which evaluates nine Apple Silicon serving engines through three lenses: speed, memory, and fidelity. We evaluate chat and agent s

SteerDuplex: Steerable Duplex Speech Dialogue Models

👍 2

09/11 08:00

Full-duplex spoken dialogue models support low-latency turn taking, interruption handling, and backchanneling, yet a key capability remains underexplored: steerability, the ability to reliably shift conversational behavior along attributes such as tone, persona, speaking rate, and voice style in res

Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations

👍 12

09/06 08:00

Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent character behavior across extended interactions. We introduce Deep Persona, a psychologically grounded, three-layered architecture that organizes pe

SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness

👍 3

09/05 08:00

Autonomous agent systems increasingly depend on reusable skill abstractions for consolidating experiential knowledge and domain expertise. These artifacts typically bundle free-form instructions with heterogeneous resources. However, ensuring their correctness remains challenging. Their failure mode

ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models

👍 2

09/02 08:00

Vision-Language-Action (VLA) models demonstrate strong generalization in robotic manipulation and navigation, but existing fine-tuning methods provide limited safety guarantees. Current approaches primarily rely on Lagrangian optimization that enforces safety through soft penalties on expected cumul

Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles

👍 3

09/02 08:00

Benchmarks for LLM-generated GPU kernels decide correctness with a few random inputs and a loose floating-point tolerance, and their verdicts now feed leaderboards and reinforcement-learning rewards. Recent work agrees these checkers are weak and patches them by hand---extra input distributions, fuz

Salvor v1.0.0-beta: I got tired of my projects forgetting what they learned, so I taught the repo to

@BlockchainDan · 18.5K 粉丝 · 3.2M 阅 · 501 赞 · 35 转

09/21 13:25

Soft-launching an open-source, repo-native engineering knowledge layer for coding agents. Built because of one very bad /clear. About a year into building an HFT tool with AI agents, I typed one

中文介绍 开源项目 Salvor v1.0.0-beta 发布，用于提高编码智能体工程知识保留效率。

Jev is INSANE for Marketing

@dsqjaffa · 737 粉丝 · 217.8K 阅 · 510 赞 · 37 转

09/21 23:15

You can't escape it. Literally EVERYWHERE you look on your feed is filled with something about "jEv is iNsAnE"... and it's generated tens of millions of views on X in less than a week. I'm guilty of

中文介绍 博主分析 jEv AI 模型的营销策略，短短一周内获得数百万次观看。

You're Already a Meat Proxy

@obie · 13.1K 粉丝 · 157.2K 阅 · 738 赞 · 98 转

09/21 05:02

I’m excited about a future that I suspect will be very hard on many long-time friends and certain people that I love. The same technology that is allowing me to be more successful than ever is

中文介绍 博主探讨科技进步对个人关系的影响，技术进步让某些人成功的同时，也让一些人感到压力。

I reverse-engineered Instinct's memory. Here's exactly how it works

@DhravyaShah · 62.1K 粉丝 · 120.2K 阅 · 509 赞 · 16 转

09/21 02:49

Instinct has taken the world by storm over the last two weeks - it's one of the best imessage assistants I've used. as with every product, I decided to reverse-engineer Instinct's memory to find out

中文介绍 博主逆向工程 Instinct 消息助手，分析其工作原理。

Jev + graphical models: a paradigm shift?

@fdellaert · 16.7K 粉丝 · 74.9K 阅 · 504 赞 · 61 转

09/21 08:19

Could Jev + graphical models fundamentally change how we build systems that reason under uncertainty? Unless you've been off the grid this week, you now know that Jev is @typesafeai’s new model for

中文介绍 博主探讨 Jev 和图形模型结合的可能性，可能改变系统推理的不确定性处理方式。

A Beginner's Guide to Jev

@omarsar0 · 320.6K 粉丝 · 73.5K 阅 · 523 赞 · 60 转

09/21 04:44

As you may have seen recently, Jev (a generalist System One model) took Twitter by storm. Many misleading examples are everywhere, but they don't really show Jev's real capabilities. Hence, we

中文介绍 博主介绍 Jev 的入门指南，纠正对 Jev 的误解。

Jev, System One models, and the future of computer use

@trycua · 19.0K 粉丝 · 59.5K 阅 · 501 赞 · 39 转

09/20 06:27

What we've been building with decision models at Cua - by @ddupont808 and @francedot Over the last few days we've deprioritized some other shiny objects because we've all been Jev-crazy. TypeSafe

中文介绍 博主介绍 Cua 公司利用决策模型与 Jev 的工作，探讨计算机使用未来。

Jev Explained for Normies

@matthewcanham · 10.7K 粉丝 · 57.1K 阅 · 516 赞 · 45 转

09/22 00:46

If you’ve been hanging out on the internet the past few days, you’ve probably come across Jev, a new AI model that’s taken the AI community by storm. Jev is not a traditional LLM. It’s built for

中文介绍 博主为非专业人士解释 Jev AI 模型，指出其与传统大型语言模型的不同。

Jev-as-a-Judge for Agent Evals

@LangChain · 265.9K 粉丝 · 46.6K 阅 · 504 赞 · 68 转

09/20 07:31

By Daniel Shea and Seán Roche Key takeways: Jev is a fundamentally different kind of evaluator. It returns typed answers directly instead of generating text like an LLM judge. Jev was dramatically

中文介绍 LangChain 推出 Jev 作为评估者，提供类型化答案，提高评估效率。

Build your own Jev (100% local)

@_avichawla · 77.5K 粉丝 · 37.8K 阅 · 593 赞 · 80 转

09/20 14:46

Everything you need to turn an open-source LLM into a fast, local decision engine without retraining it. It covers next-token scoring, fixed choices with probability distributions, SGLang, and a

中文介绍 博主介绍如何将开源 LLM 转化为本地决策引擎，无需重新训练。

Build a Jev Judge

@akshay_pachaar · 289.5K 粉丝 · 32.1K 阅 · 501 赞 · 59 转

09/22 01:26

We use LLMs to write answers, then call another LLM to judge them. But when the judgment is a handful of bounded decisions, do we need another round of text generation? An agent answers a customer

中文介绍 博主提出构建 Jev 评估者，解决判断中多个有限决策问题。

A Swarm of Fruit Flies, Building a Civilization On-Chain

@murmur_arc · 983 粉丝 · 11.8K 阅 · 553 赞 · 137 转

09/20 21:17

Prologue — No LLMs, Only Neurons This project is called murmur, and it is alive right now on Arc mainnet (Chain ID 5042), settling in real USDC. To date the flies have completed more than 23,000

中文介绍 博主介绍项目 murmur，使用神经元构建基于区块链的文明。

🔬 An Oscar, Two Asteroids, and the Algorithm in Your sklearn: John Platt on AI for Science

Latent Space · 09/23 05:07

We talked to Google’s Oscar winning “Giganerd” about automating science, solving climate change, and how future generations can contribute to science in the age of superintelligent AI

中文介绍 谷歌“奥斯卡获奖者”John Platt探讨了AI在科学领域的应用，包括自动化科学和解决气候变化问题。

Better prompt caching for GPT-6

OpenAI News · 09/23 05:00

Learn how GPT-6 improves prompt caching with higher cache hit rates, new diagnostics, explicit breakpoints, and controls that reduce latency and costs.

中文介绍 GPT-6通过提高缓存命中率、新诊断、显式断点和减少延迟和成本的控制，改进了提示缓存。

Introducing GPT-6 Sol and Luna

OpenAI News · 09/23 02:00

Meet GPT-6 Sol and Luna, two models that bring frontier intelligence to everyday work with different balances of capability and cost.

中文介绍 OpenAI推出GPT-6 Sol和Luna模型，平衡能力和成本，提高日常工作中的智能。

Roundtables: The Deadly Failures of The Virtual Border Wall

MIT Tech Review AI · 09/22 21:42

The US has spent billions building a “virtual wall” of surveillance towers along its southern border over the past 25 years, promising they will help detect and apprehend border crossers and save lives. But a groundbreaking investigation by MIT Technology Review has documented over a thousand people

中文介绍 MIT科技评论调查了美国花费数十亿美元在南部边境建立的“虚拟墙”的失败。

Parallel cut research time and cost in half with GPT‑6 Astra

OpenAI News · 09/22 20:00

GPT‑6 Astra allowed Parallel’s agents to research and synthesize labor-market data in half the time and at half the cost vs. prior models.

中文介绍 GPT-6 Astra将Parallel的代理研究劳动市场数据的时间成本减半。

Don’t be fooled by this summer of AI hype

MIT Tech Review AI · 09/22 19:04

It’s been a busy few months for AI hype. At the end of April, Anthropic claimed that its model Claude Mythos is better at finding software vulnerabilities than most security experts. Then we had the OpenAI–Hugging Face hacking incident, after which Anthropic (proudly) and Meta (reluctantly) disclose

中文介绍 MIT科技评论指出，当前夏季的AI炒作是不可信的。

[AINews] Xiaomi MiMo-V2.6-Pro 1T-A42B: the new top Open Weights model, trained for $3M

Latent Space · 09/22 14:30

crowning a new Chinese frontier lab

中文介绍 Xiaomi MiMo-V2.6-Pro 1T-A42B成为新的顶级开放权重模型，训练成本为300万美元。

Priorities and principles for effective third party assessments

OpenAI News · 09/22 08:00

OpenAI outlines priorities and principles for rigorous, secure, and independent third-party AI safety assessments of frontier models and safeguards.

中文介绍 OpenAI概述了有效第三方AI安全评估的优先级和原则。

How UK AISI and EvalEval Are Making Benchmark Results Reproducible

Hugging Face Blog · 09/22 08:00

中文介绍 UK AISI和EvalEval如何使基准结果可重现。

Transformers now runs llama.cpp quants

Hugging Face Blog · 09/22 08:00

中文介绍 Transformers现在支持llama.cpp quants。

Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community

Hugging Face Blog · 09/22 08:00

中文介绍 Jun Kim，oMLX的创建者和维护者，加入Hugging Face支持MLX社区。

Opus 5.5 imminent ⏳, Grok 4.7 🚀, MiMo v2.6 🤖

TLDR AI · 09/22 08:00

中文介绍 Opus 5.5即将发布，Grok 4.7推出，MiMo v2.6更新。

Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI

Latent Space · 09/22 06:13

The definitive Jev podcast with its lead creator.

中文介绍 Jev系统一模型由TypeSafe AI的CEO Diogo Almeida主导。

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

Hugging Face Blog · 09/21 21:44

中文介绍 像物理学家一样修剪LLMs：块移除作为Ising优化问题。

Higgsfield AI ships new video features in a day with GPT-6 Astra

OpenAI News · 09/21 20:00

With GPT-6 Astra, Higgsfield AI makes video ad creation easier for small businesses and brings new creative tools to market faster.

中文介绍 Higgsfield AI利用GPT-6 Astra推出新视频功能，为小企业简化视频广告制作并加快新创意工具上市。