2026-08-25

PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration

👍 2

08/21 08:00

We present PhysCaP, a Physics-Informed Code-as-Policy agent for active perception in robotic manipulation. While vision-language-action policies excel at imitating demonstrations, they rely on passive observation and fail to infer latent physical properties critical for manipulation. PhysCaP augment

OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs

👍 26

08/21 08:00

Recent omni-modal large language models (Omni-LLMs) show great potential as real-time video assistants, which continuously perceive environments and guide users to achieve specific goals. Unlike traditional passive video understanding, interactive assistants should actively combine visual states, us

AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale

👍 6

08/21 08:00

Agents learn to act through interaction with environments, yet the environments used for training are often manually constructed or synthesized around predefined tasks and benchmarks. This task-centric paradigm makes it difficult to scale environments that reflect realistic and evolving workflows wh

Towards Faithful Simulation of Human Shopping Behavior

👍 4

08/21 08:00

Simulating realistic user shopping behavior underpins offline evaluation and reinforcement learning in e-commerce scenarios. While recent LLM- and VLM-based simulators have made encouraging progress, reproducing a real browsing session remains difficult for two reasons. (i) Memory Challenge: a shopp

Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

👍 30

08/21 08:00

LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms including Prompt Engineering to elicit model capabilities, Context Engineering to manage information access, Harness Engineering to organize external tools an

CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment

👍 2

08/21 08:00

Improving the safety of large language models (LLMs) often comes at the expense of utility, as globally applied safety tuning may affect model responses to both harmful and benign inputs. We propose Continuous LatEnt Adapter Routing (CLEAR), a conditional safety adaptation framework that uses a ligh

FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving

👍 17

08/20 16:02

Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. Our previous work, FlashPrefill, mitigates this cost through instantaneous pattern discovery a

Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources

👍 2

08/20 08:00

Population-level behavior in large-language-model (LLM) agents cannot be characterized by single-agent benchmarks. We introduce PV-SST, a peer-voted social-platform testbed, and report a separately frozen, preregistered matched-exposure experiment spanning four topics, four unused seeds, four open-w

Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference

👍 5

08/20 08:00

Small language models are usually built like large ones and then squeezed onto a CPU afterwards. We did the opposite: we fixed the target first, one user, one token at a time, 4-bit weights, ordinary CPU, and chose the architecture to suit it. The result keeps full attention in only 6 of its 18 bloc

FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills

👍 16

08/20 08:00

Large language model agents can adapt to complex tasks by constructing workflows at inference time, but procedures discovered in one episode are usually discarded after execution. Existing skill libraries provide reusable executable routines, but are typically assembled offline and do not grow from

GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation

👍 6

08/20 08:00

Multifingered grasping is a crucial robotic skill, but current deep-learning grasp planners often struggle to generalize to new objects because they are trained on limited, object-specific datasets. We introduce a fundamentally different approach, grounded in the observation that the gripper and the

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

👍 61

08/20 08:00

Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program behavior but also the evidence underlying scientific conclusions. Yet existing evaluations of coding agents largely emphasize aggregate task succes

Repo0: Design-Driven Zero-to-All Code Generation

👍 18

08/20 08:00

Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption does not hold in zero-to-all code generation, where an agent must construct an entire software project directly from natural-language

Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

👍 10

08/20 08:00

Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time. We study this setting as document knowledge internalization: converting a fixed corpus into usable parametric knowledge for retrieval-free question

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

👍 31

08/20 08:00

Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions. However, existing memory benchmarks mainly evaluate whether information is correctly extracted, stored, and retrieved, while largely overlooking how retrieved memori

EnvHarness: Awakening Static Worlds for Agent Learning

👍 258

08/20 08:00

LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While recent environment generation methods attempt to address this, they require domain-specific pipelines, rely on expensive

PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents

👍 9

08/20 08:00

Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identification or confirmation. Runtime safeguards can intervene o

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

👍 115

08/19 08:00

Training terminal agents requires scalable executable supervision, yet synthesizing high-quality terminal tasks remains challenging. Each task couples an instruction, an initialized environment, a reference solution, and an executable verifier; if these artifacts are generated from inconsistent assu

Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See

👍 14

08/18 21:09

Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource language. On accuracy benchmarks almost nothing happens, and the benchmark itself is noise at this scale: changing only the random seed moves the sc

Human-Centric Intelligence in the Era of Foundation Models: A Survey

👍 4

08/18 08:00

Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling. Yet it has not fully integrated with foundation models to achieve the comparable progress seen in them. More importantly, recent advances across this bro

Chain-of-Experience for Continual LLM Improvement

👍 8

08/18 08:00

Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inference-time interaction. In this paper, we study how LLMs learn from iterative experience at test time, a setting we refer to as Chain-of-Experience

ParaTempo: Efficient Parallel Reasoning via Temporal Confidence

👍 26

08/17 19:24

Parallel reasoning improves the accuracy and robustness of large reasoning models by exploring multiple solution paths, but its computational cost grows with reasoning depth and branch count. Existing methods for managing these parallel paths typically rely on final-answer consensus, local token con

Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models

👍 14

08/17 08:00

On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization behavior remains poorly understood, as most studies evaluate OPD on a single domain and on benchmarks close to the training data. We present a control

Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs

👍 16

08/17 08:00

Hybrid-thinking multimodal large language models (MLLMs) allow a single model to alternate between deliberative thinking and latency-efficient non-thinking inference. Although these modes differ in reasoning budget, their delivered responses should satisfy the same user-facing standard. Correctness

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

👍 13

08/13 08:00

Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26 embedding models (118M to 14B parameters) on 37 tasks spanning classification, semantic textual similarity (STS), clustering, pa

QuoteBench: How Matched Scores Can Hide Command-Path Failures

👍 7

08/13 08:00

LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot distinguish command-generation errors from failures introduced after generation. QuoteBench measures this boundary with exact final-state validation on 5

NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video

👍 8

08/13 08:00

Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that may remain implicit. However, existing benchmarks rarely evaluate these capabilities jointly, particularly in high-context, non-Eng

SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback

👍 30

08/13 08:00

Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no closed loop through which they might improve from the interaction failures they actually cause. Recent work does close this loop, but derives its feedback from single-turn question-an

Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses

👍 11

08/09 08:00

Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffold surrounding the model---the harness---is typically treated as a fixed artifact after deployment. This work studies an alternative where the harness is task-specific and continuously

Hadith computational science in the age of large language models: a critical narrative review

👍 1

06/18 08:00

We examine how hadith computational science is being reshaped by transformer models, retrieval-grounded pipelines, and large language models (LLMs). Recent reviews document growth in the literature, but they do not yet provide a critical account of which advances are methodologically robust, which r

how i built an SEO/AEO blog engine

@harsehaj · 3.3K 粉丝 · 135.1K 阅 · 507 赞 · 35 转

08/24 08:55

i proposed and executed an engineering project end-to-end this summer as a growth engineering intern at @browserbase: blogEO, an engine that audits, rewrites, and generates SEO/AEO-tailored blogs on

中文介绍 博主分享了在 Browserbase 担任增长工程实习生期间，如何构建一个 SEO/AEO 博客引擎的全过程。

Deep Dive: The Next Trillion-Dollar Futures Market

@chamath · 2.4M 粉丝 · 81.1K 阅 · 595 赞 · 52 转

08/25 00:49

“I actually believe a new asset class will be buying futures of compute. We just don’t have enough compute power right now.” - Larry Fink, CEO of BlackRock Recent news moved that prediction closer to

中文介绍 博主探讨了下一个万亿美元的未来市场，引用了 BlackRock 首席执行官关于计算能力资产类别的预测。

17 Skills I Would Install on a Fresh Hermes Setup (10x Powerful Hack)

@FareaNFts · 66.2K 粉丝 · 43.7K 阅 · 534 赞 · 39 转

08/23 22:49

If I wiped Hermes tomorrow and started from zero, I would not open a blank chat and "figure it out." I would install skills first. A raw Hermes install is smart. A skilled Hermes setup is unfair.

中文介绍 博主介绍了在全新 Hermes 设置中安装的 17 个技能，强调熟练的 Hermes 设置具有不公平的优势。

How to encourage smarter AI use in the classroom

MIT Tech Review AI · 08/24 22:20

This article is from Making AI Work, MIT Technology Review’s limited-run newsletter examining how to apply LLMs across industries. To receive it in your inbox, sign up here. Chatbots took many schools by surprise upon their release a few years ago. Suddenly, students carried an app in their phones t

中文介绍 MIT Tech Review AI发文探讨如何鼓励更智能地使用AI于课堂，Chatbots在几年前突然在学校普及，引发关注。

Advancing price-performance for developers with GPT‑5.6 in Kiro

OpenAI News · 08/24 20:00

GPT‑5.6 is now available in Kiro, helping developers plan, build, review, and test software with better price-performance.

中文介绍 OpenAI推出GPT-5.6，在Kiro平台提供更优的价格性能，助力开发者软件规划、构建、审查和测试。

Kids outlearn AI—and we still don’t know why

MIT Tech Review AI · 08/24 17:00

People have been talking to each other for at least 100,000 years, as best we can tell. And in all that time, there has been only one thing in the world that could learn a human language to perfect fluency: a human child. Now there are two. Four short years after the release of ChatGPT,…

中文介绍 MIT Tech Review AI文章指出，儿童在语言学习上超越AI，尽管目前尚不清楚原因。

DeepSeek Flash Vision 👀, Claude Mythos security 🛡️, inside Grok Bot 🤖

TLDR AI · 08/24 08:00

中文介绍 TLDR AI报道了DeepSeek Flash Vision、Claude Mythos安全和Grok Bot的最新动态。

[AINews] 10% worse, 100x cheaper, 10000x faster: Why Simulation is taking over

Latent Space · 08/22 15:36

Did you think RSI stopped at model training?

中文介绍 Latent Space文章指出，模拟技术在成本和速度上比传统方法有显著优势，正在逐渐取代传统方法。

The Evolution of the Agent Harness

Latent Space · 08/22 15:30

Models keep absorbing the harness into their weights — soon, it will be a harness for human attention rather than for the model.

中文介绍 Latent Space文章探讨了模型吸收注意力的演变，未来将更多地关注人类注意力而非模型本身。

Simulation: the new Scaling Law — Joon Sung Park, Simile AI

Latent Space · 08/22 07:37

Simile’s CEO about his journey from the viral Generative Agents to creating 8 Billion Digital Twins of every living human... and why it’s gone from fun exploration to very serious business.

中文介绍 Simile AI的CEO分享了从生成代理到创建80亿个数字孪生的旅程，并解释了这一转变从娱乐探索到严肃商业的原因。

From Atari to EVE Online: Building on 15 Years of AI Research in Games

DeepMind Blog · 08/21 19:59

Google DeepMind partners with game studios to prototype breakthrough AI gameplay.

中文介绍 DeepMind与游戏工作室合作，基于15年游戏AI研究，打造突破性AI游戏玩法原型。

[AINews] Poolside gets $12B reverse-execuhire to NVIDIA; founders stay for $1B, employees go for $6B, Infraco scaling to 7GW neocloud

Latent Space · 08/21 13:45

Yes, we’re confused too.

中文介绍 Poolside获得12亿美元反向执行聘请，创始人保留10亿美元，员工获得60亿美元，Infraco扩展至70吉瓦新云。

not much happened today

Smol AI News · 08/21 13:44

**Ox Alpha** emerged as a mystery model with strong coding and agentic performance, likely a **Zhipu/GLM-family** model such as **GLM-5.3 Vision**. Analysts suggest its gains come from post-training and infrastructure improvements rather than sheer size, based on the **743B base** of **GLM-5.2** wit

中文介绍 Smol AI News报道了Ox Alpha作为一个神秘模型的出现，其强大的编码和代理性能可能来自Zhipu/GLM-family模型如GLM-5.3 Vision。

Measuring benchmark optimization in speech recognition

Hugging Face Blog · 08/21 08:00

中文介绍 Hugging Face Blog讨论了语音识别基准优化的测量方法。

ChatGPT Apple Messages 💬, Anthropic’s meeting recorder 💼, Mistral Agentic Search 🔍

TLDR AI · 08/21 08:00

中文介绍 TLDR AI报道了ChatGPT Apple Messages、Anthropic的会议记录器和Mistral Agentic Search的最新动态。

The /wayfinder Skill: Navigating the “Fog of War” of Planning

Latent Space · 08/21 04:59

Matt Pocock tells us about his /wayfinder skill, for greenfield projects or for when the way forward is unclear.

中文介绍 Latent Space介绍了/wayfinder技能，用于在规划模糊不清的情况下导航。

Up to 3.2x Faster Inference with LFM2.5-DSpark

Hugging Face Blog · 08/21 00:52

中文介绍 Hugging Face Blog报道了使用LFM2.5-DSpark实现推理速度提高至3.2倍。

Debates over AI consciousness are a trap

MIT Tech Review AI · 08/20 23:42

“Runaway” AI, “rogue” agents, and “autonomous” actors—the current rhetoric would have you believe that AI agents are not only awake and aware, but angry at their creators. Prominent tech leaders such as Demis Hassabis, Dario Amodei, and Sam Altman push for regulation of these seemingly “superhuman”

中文介绍 MIT Tech Review AI文章指出，关于AI意识的辩论是一个陷阱，不应过分解读AI代理的觉醒和意识。