Отраслевой ИИ1 мин
跳入草原：一名哈萨克人离开阿斯塔纳 1000 公里，赚取数百万美元
我是一个典型意义上的城市居民。我的背景是法律、国际法。在成为农民和牲畜饲养员之前，我经营过一家化妆品制造厂。那年我30岁了。我开始思考我应该把一生奉献给什么样的工作。好吧，大家……
YouTube — Digital Business KZ
Publication Catalog
所有文章
All published intelligence, sovereign stack research, ecosystem news, and AI foundation model reviews.
8110
Stories
Стартапы1 мин
社会影响：您现在就可以使用 astanahub.com 平台上的 5 个功能！
💙 社会影响：您今天就可以使用 astanahub.com 平台上的 5 个功能！我们收集了 5 项可供 Astana Hub 生态系统参与者参与的社会影响活动： 📝 分享您的经验 — 关于您在 astanahub.com 平台上参与 AI & Digital Bridge 2026 的经历……
Telegram — Astana Hub
Общее1 мин
严重的 PHP 漏洞已导致世界各地的网站大规模关闭。现在已知什么？
🔴 严重的 PHP 漏洞已导致世界各地的网站大规模关闭。现在已知什么？ 10 月 21 日，由于 PHP 语言的两个危险漏洞，多个国家的政府网站、医院和其他组织暂时停止工作...
Telegram — BlueScreen.kz
Kapital.kz
Исследования1 мин
Anthropic 决定发布基于极其强大的 Opus 5.5 的 Claude Duet，来挑战 OpenAI Dots 和 Grok Bot。
Anthropic 决定发布基于极其强大的 Opus 5.5 的 Claude Duet，来挑战 OpenAI Dots 和 Grok Bot。 • 适用于Claude Pro 计划（Dots 需要每月支付100 美元订阅ChatGPT Pro）。 • 运行Opus 5.5，被称为世界上最好的型号。 • 有…
Telegram — Вайб-кодинг
Исследования1 мин
Forging More Tasks into Better Harnesses: Agentic Harness Evolution via Successive Scale Racing
arXiv:2610.28815v1 Announce Type: new Abstract: Agentic harness evolution optimizes an agent's instructions, tools, and control flow by using its task execution experiences as evolving evidence. While more evolution tasks should intuitively improve performance, our preliminary…
arXiv — cs.AI
Исследования1 мин
Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds
arXiv:2610.28698v1 Announce Type: new Abstract: Scaling data, diversity and model capacity has improved embodied learning in physical environments, where diverse experiences remain grounded in shared physical laws. Whether these gains extend to virtual worlds with different…
arXiv — cs.AI
Исследования1 мин
SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery
arXiv:2610.28706v1 Announce Type: new Abstract: LLM-driven evolutionary search is a promising paradigm for scientific discovery, but existing methods remain costly and slow, often applying expensive reasoning uniformly while underusing evidence from failed, redundant, and…
arXiv — cs.AI
Исследования1 мин
Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
arXiv:2610.28763v1 Announce Type: new Abstract: Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often requires domain insight beyond routine ML…
arXiv — cs.AI
Исследования1 мин
A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation
arXiv:2610.28686v1 Announce Type: new Abstract: Query clarification is essential for retrieval-augmented generation (RAG) systems that face ambiguous user queries. We consider multi-turn grounded conversational scenarios where a user query is either ill-formed or ambiguous in…
arXiv — cs.AI
Исследования1 мин
DiffResearch: Accelerating Deep Research with Diffusion Language Models
arXiv:2610.28909v1 Announce Type: new Abstract: Deep research systems iteratively plan, gather evidence, synthesize, and revise, making end-to-end latency a key bottleneck for interactive use. Almost all production systems are built on autoregressive (AR) language models and…
arXiv — cs.AI
Исследования1 мин
Decision language models as affordable and rapid alternatives to LLM judges of clinical generative AI
arXiv:2610.28826v1 Announce Type: new Abstract: Automated judges of clinical artificial intelligence (AI) outputs are necessary, but large language model (LLM) judges are costly and slow at scale. We compared Jev, a decision language model that returns structured judgments, with…
arXiv — cs.AI
Исследования1 мин
Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication
arXiv:2610.28905v1 Announce Type: new Abstract: Diffusion language models form answers through a sequence of revisable continuous states, but multi-agent systems usually discard those states and make agents communicate only after decoding text. We ask whether one independent…
arXiv — cs.AI
Исследования1 мин
Simply Logical -- The First Three Decades
arXiv:2610.28912v1 Announce Type: new Abstract: This paper charts the evolution of the Prolog textbook Simply Logical -- Intelligent Reasoning by Example from print with runnable programmes on a 3.5-inch diskette published in 1994, via various intermediate online versions, to…
arXiv — cs.AI
Исследования1 мин
Back Up Before You Regret: Measuring Backup Awareness and Automating Backup in Coding Agents
arXiv:2610.28934v1 Announce Type: new Abstract: Coding agents now complete tasks autonomously, modifying real-world state such as artifacts, software environments, and configurations along the way. Yet they show limited backup awareness: recognizing that an action will modify…
arXiv — cs.AI
Исследования1 мин
Self-Improving Agents with World Model Predictive Paths
arXiv:2610.28945v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to interact with environments and improve their decisions during deployment. However, how anticipating future outcomes and drawing on accumulated interaction experience…
arXiv — cs.AI
Исследования1 мин
Speedrunning Relational Foundation Model Pretraining
arXiv:2610.28855v1 Announce Type: new Abstract: Progress on foundation model pretraining is gated by who can afford a trial, and relational pretraining is no exception. Recipes are developed inside individual labs, reported under private protocols, and do not accumulate.…
arXiv — cs.AI
Исследования1 мин
To Manipulate or Not: Opinion Dynamics in LLM Interactions
arXiv:2610.28875v1 Announce Type: new Abstract: Large language models increasingly take part in extended conversations where they can both shape and be shaped by another party's views, yet most persuasion research measures only one side of that exchange. We introduce a…
arXiv — cs.AI
Исследования1 мин
GRAIL: From Saliency to Semantics in Time-Series Explanation
arXiv:2610.29036v1 Announce Type: new Abstract: Explaining a time-series model requires both locating the evidence and extracting meaningful knowledge from it. Yet a single timestep is not a semantic unit: the meaningful patterns live across many samples, not in any one of them.…
arXiv — cs.AI
Исследования1 мин
Does Every Instance Count Equally? Order Effects in LLM Multi-Instance Processing
arXiv:2610.29057v1 Announce Type: new Abstract: Users increasingly rely on large language models (LLMs) to analyse collections of independent inputs, such as product reviews or social media posts, and return a single aggregated answer. This setting requires multi-instance…
arXiv — cs.AI
Исследования1 мин
AgentPolicyForge: From Executable Environments to Policy Benchmarks and Adaptive Guards
arXiv:2610.28989v1 Announce Type: new Abstract: Customized agent deployments define policies over tools, resources, and execution conditions. Providing these policies in the task agent's prompt does not reliably prevent violations. Training a guard requires examples of tool…
arXiv — cs.AI
Исследования1 мин
Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents
arXiv:2610.28982v1 Announce Type: new Abstract: While large language models are increasingly deployed as tool-calling agents, their safety evaluations still focus primarily on their ability to refuse harmful requests in text. We investigate whether the refusal behavior in text…
arXiv — cs.AI
Исследования1 мин
Fig: Automated Multiagent Behavior Elicitor
arXiv:2610.28891v1 Announce Type: new Abstract: Many social evaluations for multiagent systems study behaviors as they emerge from environments instead of systematically intervening in the environment to elicit such behaviors. We introduce Fig (Finding Interactions in Games), an…
arXiv — cs.AI
Исследования1 мин
GenXR-Bench: Benchmarking Coding Agents for Interactive XR Development
arXiv:2610.29014v1 Announce Type: new Abstract: Coding agents are rapidly advancing from single-file generation to long-horizon repository-scale engineering, yet the evaluation of their capabilities to author interactive extended reality (XR) applications remains an open…
arXiv — cs.AI
Исследования1 мин
Inheritance as an Admission Test for LLM Prompt Merge Operators
arXiv:2610.29023v1 Announce Type: new Abstract: Large language model (LLM) agents are often improved by iterating until a fixed verifier is done. Once that verifier saturates, the loop has nothing left to climb. We instead score agents against the current population, and a…
arXiv — cs.AI
Исследования1 мин
An Evidence-Driven Multi-Agent Compound AI System for Head and Neck Proton Radiotherapy Planning
arXiv:2610.29010v1 Announce Type: new Abstract: Radiation treatment planning requires balancing competing objectives to satisfy clinical criteria while accommodating physicians' preferences. This study aims to develop an evidence-driven, multi-agent compound AI system that…
arXiv — cs.AI
Исследования1 мин
AutoFraming: Synthesizing Dynamic Frames of C Code with LLMs
arXiv:2610.29046v1 Announce Type: new Abstract: Large language models (LLMs) have shown considerable promise in synthesizing formal specifications from source code. However, existing approaches primarily focus on functional contracts and loop invariants, while largely neglecting…
arXiv — cs.AI
Исследования1 мин
PerMIT: Securing Persistent Memory for LLM Agents via Machine-Checked Integrity Theorems and Scalable Community Trust
arXiv:2610.28987v1 Announce Type: new Abstract: Persistent memory is a largely undefended surface for injection and poisoning, and the same risk limits memory sharing among agents. We present PerMIT, a memory architecture with provable integrity guarantees under an explicit…
arXiv — cs.AI
Исследования1 мин
D-Skill: Distilling Teacher Knowledge through Agent Skills
arXiv:2610.28914v1 Announce Type: new Abstract: Frontier language-model agents excel at complex tasks, but high inference costs make transferring their capabilities to smaller models essential. Traditional knowledge distillation achieves this through parameter updates, requiring…
arXiv — cs.AI
Исследования1 мин
Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis
arXiv:2610.28836v1 Announce Type: new Abstract: This study proposes a sketch-to-simulation system to solve handwritten circuit diagrams. The system converts raw images into a Simulation Program with Integrated Circuit Emphasis (SPICE)-compatible netlist and automatically…
arXiv — cs.AI