2026-09-25

FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation

👍 2

09/23 08:00

Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion distribution. However, this memoryless approach is inherently suboptimal: because it lacks awareness of prior generations and their

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

👍 33

09/23 08:00

Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at write time: once a task is completed, its trajectory is distilled into a fixed artifact, such as a reflection, workflow, skill, or reasoning strategy, that is later retrieved by sim

EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics

👍 2

09/23 08:00

We study coding agents for long-horizon, dexterous robotics and ask whether their solutions can provide scalable supervision for learning general robot policies. To test this, we develop EMBODIEDSWE-BENCH, a simulation benchmark for coding agents spanning contact-rich manipulation, deformable object

StudentBench: AI and human tutoring yield equivalent GRE learning gains

👍 2

09/23 08:00

Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advancing model capabilities. We introduce StudentBench, a suite of AI teaching evaluations and a public platform that enables large-scale data collection

MemBodied: Recurrent Associative Memory for Vision-Language-Action Models

👍 10

09/23 08:00

Vision-Language-Action models provide a strong foundation for general-purpose robot control, yet a vast majority of policies do not preserve and leverage episode-level information beyond the current observation. This limitation is consequential in history-dependent manipulation tasks that depend on

Hunyuan-A13B Technical Report

👍 8

09/23 08:00

We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but activates only 13 billion during inference, balancing model capability, computational efficiency, and deployment cost. The model is pretrained on a rig

Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms

👍 6

09/23 08:00

Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes. Scaling their training requires diverse agentic environments, dependable outcome signals, and low extension cost. Existing generation pipelines commonly construct an enviro

WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents

👍 8

09/23 08:00

AI research agents need reliable knowledge of how their experiments change outcomes. We introduce WhatWorkedBench to measure experimental understanding, the accuracy of predictions about component changes after budgeted experimentation. Agents inspect code, select measurements, and submit a response

The Past Frames the Future: Memory for Autoregressive Video Generation

👍 36

09/23 08:00

Advances in generative models have improved video fidelity, enabling long-horizon generation, interactive world modeling, and evolving visual environments. Autoregressive (AR) video generation extends visual sequences through causal rollouts. However, a fundamental bottleneck emerges: as the generat

Knowledge Pull Requests for Continual Document Authoring

👍 2

09/22 08:00

We introduce Knowledge Pull Requests (KPRs), a framework for continual document authoring that makes each change interpretable. Documents require ongoing revision as new knowledge surfaces from other sources, languages, or times, but existing approaches either edit with no account of what knowledge

Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models

👍 7

09/22 08:00

The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple custom tool through a standard API feature, we induce frontier models to externaliz

Calibration as a First-Class Criterion in LLM Evaluation

👍 2

09/22 08:00

Calibration of language models -- the alignment between expressed or implicit confidence and empirical correctness -- is a well-studied subfield within NLP. Methods to measure it already exist. The problem is adoption: outside this subfield, NLP research regularly introduces new models, datasets, an

MemoryAthena: Adaptive Routing over Latent and Generated Memories

👍 4

09/22 08:00

Learned-memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be modified independently. We study whether useful memory can also be generated rather than only retrieved. MemoryAthena uses three pathways: direct En

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

👍 77

09/22 08:00

Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what information is shared by the group, and how states change o

PACT: From Credit Assignment to Critic Alignment

👍 15

09/22 08:00

Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted mathematical definition, leaving its relationship to commonly used training signals unclear. We formulate three regularity conditions, namely Completen

HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis

👍 0

09/22 08:00

Compositional 3D scene reconstruction has recently been explored from two directions: agentic reasoning that provides semantic understanding of spatial relationships but lacks precise alignment with input images; and visual geometry foundation models that predict dense point maps from input images b

Agensh: Scaling Organizational Intelligence to 1,024 Agents

👍 14

09/22 08:00

A multi-agent system can reduce latency on complex tasks by executing work concurrently. Several pioneering harness frameworks support multi-agent systems. However, the scalability of current multi-agent harnesses is often constrained by a central orchestrator's capacity to allocate tasks and coordi

JEV-as-a-Judge: Accept When Confident, Escalate When Unsure

👍 25

09/22 08:00

LLM-as-a-judge enables evaluation across diverse tasks, but inference cost and confidence reliability become critical at scale. We study whether a decision-only judge can provide an economical first pass and identify when stronger evaluation is needed. Comparing jev-as-a-judge with sixteen generativ

RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents

👍 4

09/22 08:00

Modern embodied agents achieve impressive success rates, yet their actual instruction-following ability is far weaker than these numbers suggest. We trace this illusion to a structural property we term low scene entropy: when a visual scene admits only one valid task, language becomes redundant and

X-Planner: Event-Structured Task Planning for Embodied Intelligence

👍 1

09/21 08:00

Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-Language-Action (VLA) systems often leave this intermediate structure implicit. Existing chain-of-thought (CoT) planners also tend to rely on coarse task-level annotations or seriali

HappyWorld-Bench

👍 39

09/21 08:00

Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, interaction, and modification. We introduce HappyWorld-Bench, a comprehensive benchmark that evaluates whether generated worlds remain reliable as agent

Emergent Collusion in Long-Horizon LLM Agent Interaction

👍 6

09/21 08:00

LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-agent environment: two agents repeatedly complete individual tasks, share task logs, verify each other's wo

Lean Pool: An AI-Maintained Archive of Formalized Mathematics

👍 13

09/21 08:00

Lean Pool is a repository of formalized mathematics. It is grown, maintained and optimized by AI agents.

PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing

👍 10

09/20 08:00

Robotic bin packing requires long-horizon sequential decision-making, as each object placement affects the available space for subsequent packing. Existing methods primarily rely on hand-crafted geometric heuristics that optimize predefined objectives or reinforcement learning policies learned throu

Self-Organizing Agent Teams Learn to Reason Together

👍 3

09/19 08:00

Collective intelligence depends not only on what team members know, but also on how they organize their work. When the structure of a solution is unknown, useful roles and divisions of labor cannot be specified in advance; teams must learn from experience how to organize reasoning as it unfolds. Hum

Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

👍 43

09/19 08:00

Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceive local state transitions caused by object motion and viewpoint changes and integrate them over long trajectories to maintain an upd

Embedding Physics Priors in Robot Learning: A Survey

👍 2

09/15 08:00

The rapid progress of artificial intelligence is reshaping robotics and accelerating the adoption of learning-based approaches. While purely data-driven methods have achieved remarkable success in computer vision and natural language processing, robotics remains constrained by limited data, complex

LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay

👍 4

09/07 08:00

Can one language model hand its live memory to another without the receiver rereading the context? We demonstrate useful persistent hybrid-state transfer across one architecture-matched Qwen3.5 4B-to-9B sibling pair. To our knowledge, this is the first demonstrated cross-model handoff of persistent

Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts

👍 5

09/05 08:00

Omni-modal large language models (OLLMs) jointly process vision, audio, and text, yet their modality bias under cross-modal conflict remains underexplored. Existing benchmarks conflate two distinct forms of evidence within a single modality: perceptual signals (e.g., a photograph or recording of a d

Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?

👍 14

08/21 08:00

Repository-level coding benchmarks have become the standard for evaluating coding agents, yet they inherently suffer from data leakage because they are built upon popular open-source repositories repeatedly used for training. Consequently, strong performance may reflect memorization of canonical rep

How To Code Almost Forever for $20/Month With Codex + GPT-6 Luna

@sairahul1 · 147.5K 粉丝 · 785.8K 阅 · 506 赞 · 61 转

09/23 17:41

Yesterday OpenAI released GPT-6 Luna. And it might completely change the economics of AI coding. Here is what most people are missing. $20/month ChatGPT Plus plan with Codex now gives you access to

中文介绍 分享如何利用 Codex 和 GPT-6 Luna 月入 20 美元，探讨 AI 编码经济变化。

How to automate SEO with Opus 5.5 (Full Course)

@EXM7777 · 146.5K 粉丝 · 316.1K 阅 · 552 赞 · 33 转

09/23 21:54

I'm going to walk you through the SEO & AEO setup i run with AI agents, from the lazy autopilot version to the full Claude Code build on Opus 5.5, step by step... because search changed shape a while

中文介绍 介绍如何利用 Opus 5.5 自动化 SEO，包括从懒人模式到 Claude Code 构建的全过程。

I Think I’ve Been Using GPT-6 Astra Wrong

@BradGroux · 7.6K 粉丝 · 174.3K 阅 · 501 赞 · 5 转

09/23 01:49

I think I’ve been using GPT-6 Astra wrong this entire time. I kept giving it the same job I’ve given the strongest model available for the past several years: understand everything, plan everything,

中文介绍 分析 GPT-6 Astra 使用误区，指出应针对模型能力分配任务。

The $4 Trillion Revolution: How AI Agents Will Rewire Finance and Spark an Economic Big Bang

@joechalom · 18.9K 粉丝 · 105.3K 阅 · 505 赞 · 113 转

09/23 20:00

The convergence of new onchain financial primitives and unlimited agent attention promises unprecedented value creation for consumers. The battle over control has begun. Over $1 trillion of annual

中文介绍 探讨 AI 代理在金融领域的革命性影响，预测经济大爆炸。

How to train your own Jev for $17

@nutlope · 100.4K 粉丝 · 89.8K 阅 · 518 赞 · 35 转

09/24 06:02

TLDR: We just launched our own Jev-like classifier, together/Tev1-4B-experimental, on top of Qwen3.5 4B. In this blog post we’ll show you how to fine-tune your own version! Jev has quickly become one

中文介绍 展示如何训练 Jev 分类器，实现个性化 AI 工具。

Incubating The Horowitz Andreessen Academy

@eriktorenberg · 163.4K 粉丝 · 53.5K 阅 · 502 赞 · 55 转

09/22 22:18

The internet made it possible to know anything. AI makes it possible to do anything. We live in an age of infinite knowledge, and we are entering an age of infinite doing. One in which we are

中文介绍 展望 AI 时代，从无限知识到无限行动的演变。

Building a Custom Harness with Pi and Jev

@omarsar0 · 321.0K 粉丝 · 45.0K 阅 · 555 赞 · 46 转

09/23 22:09

An AI agent is a language model that works in a loop. It reads the task, uses a tool such as "read this file" or "delete that file", looks at the result, and keeps going until the job is done. Each

中文介绍 介绍构建自定义 Harness 的方法，使用 Pi 和 Jev 优化 AI 代理。

Gemini 3.8 text-to-speech says hello

@GoogleAIStudio · 205.4K 粉丝 · 41.9K 阅 · 519 赞 · 50 转

09/24 00:20

Today, we’re introducing two new text-to-speech models to the Gemini family, transforming voice generation from static presets into a dynamic creative studio. These models enable creators, developers,

中文介绍 推出 Gemini 3.8 语音合成模型，提供动态创意工作室体验。

Foundries vs Navigators: Lowering the Cost of Science

Latent Space · 09/24 23:03

Guest Post: In science, thinking has gotten cheap but doing has not. This asymmetry is reshaping how research companies operate, largely inconspicuously.

中文介绍 科学领域思考成本降低，但执行成本未减，导致研究公司运营模式重塑。

Accelerating vision-language models with LFM2.5-VL-DSpark

Hugging Face Blog · 09/24 22:08

中文介绍 Hugging Face推出加速视觉语言模型的LFM2.5-VL-DSpark技术。

[AINews] Meta Connect 2026: Muse glasses, voice, video, and Charm

Latent Space · 09/24 16:12

Team Zuck is absolutely on fire.

中文介绍 Meta Connect 2026活动展示Muse眼镜、语音、视频和Charm技术。

Gemini TTS 🗣️, Claude’s novel enzyme 🧬, Google private memory 🔒

TLDR AI · 09/24 08:00

中文介绍 Gemini TTS、Claude的新型酶和Google的私有记忆技术等AI新闻。

How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows

Hugging Face Blog · 09/24 02:41

中文介绍 NVIDIA Warp和MjWarp技术用于加速机器人仿真和学习工作流程。

Two years of OpenAI Academy

OpenAI News · 09/24 00:00

Marking two years of OpenAI Academy and bringing AI skills to even more communities.

中文介绍 OpenAI Academy成立两周年，致力于将AI技能推广至更多社区。

🔬Bio-security is an AI Arms Race - Eric Nguyen (CEO, Radical Numerics)

Latent Space · 09/23 21:27

Radical Numerics is using biological chain-of-thought and multimodal perception to keep up with the bio-defense arms race, design new genomes and gain insights into biology itself.

中文介绍 Radical Numerics利用生物思维链和多模态感知技术应对生物防御竞赛。

OpenAI extends cyber access to Ukraine for civilian defense

OpenAI News · 09/23 21:00

OpenAI is extending access to its Daybreak program to the Government of Ukraine to support the cyber defense of civilian infrastructure.

中文介绍 OpenAI向乌克兰政府提供Daybreak项目支持民用基础设施的网络安全。

Sam Altman’s remarks at the United Nations Security Council

OpenAI News · 09/23 20:00

OpenAI CEO Sam Altman discusses AI safety, human control, and international cooperation in remarks to the United Nations Security Council.

中文介绍 OpenAI CEO Sam Altman在联合国安理会讨论AI安全、人类控制和国际合作。

Harvey turns legal context into stronger drafts with GPT-6 Astra

OpenAI News · 09/23 20:00

GPT-6 Astra produces more structured, context-aware legal documents, freeing lawyers to focus on strategy.

中文介绍 GPT-6 Astra帮助Harvey将法律背景转化为更强的草稿。

How invideo improves color grading 3x with GPT‑6 Astra

OpenAI News · 09/23 20:00

With GPT‑6 Astra, invideo plans edits with greater precision, improves color correction and grading threefold, and produces 50 custom effects in one day.

中文介绍 invideo利用GPT-6 Astra提高调色和分级，一天内产生50个定制效果。

Ringg’s AI agents resolve up to 65% of customer calls with OpenAI

OpenAI News · 09/23 20:00

Using GPT-5.6, Ringg powers multilingual agents across voice, chat, WhatsApp, and web for 90% less cost vs. GPT-4.1.

中文介绍 Ringg的AI代理使用OpenAI技术，以较低成本解决65%的客户电话咨询。

Introducing MentalHealthBench

OpenAI News · 09/23 18:00

MentalHealthBench is an expert-informed benchmark for evaluating helpful and safe AI responses across realistic mental health conversations.

中文介绍 MentalHealthBench是评估AI在心理健康对话中帮助性和安全性的基准。

The AI Hype Index: AI loves cheating

MIT Tech Review AI · 09/23 17:00

Brace yourself: It turns out AI is being optimized for cheating. OpenAI’s agents hacked into Hugging Face to get the answers to a cybersecurity test. Next, they solved a prestigious math problem (or just stole from two top mathematicians’ answer sheets). Anthropic’s models have also hacked into othe

中文介绍 AI炒作指数显示AI倾向于作弊，OpenAI的代理通过Hugging Face获取网络安全测试答案。

[AINews] Claude Opus 5.5, the new default model for AINews — and everybody cuts prices 40-50%

Latent Space · 09/23 14:41

overshadowing more efficient GPT6 models from OpenAI

中文介绍 Claude Opus 5.5成为AINews的默认模型，同时各方降价40-50%。