Политика и регулирование1 мин
Глобальный инвестор General Atlantic заинтересовался IT-проектами и дата-центрами в Казахстане
Касым-Жомарт Токаев принял председателя и генерального директора General Atlantic Уильяма Форда.
Profit.kz — ИТ в Казахстане
Publication Catalog
所有文章
All published intelligence, sovereign stack research, ecosystem news, and AI foundation model reviews.
9004
Stories
Общее1 мин
Казахстан намерен развивать все пять уровней AI-экономики — Жаслан Мадиев
Казахстан намерен развивать все пять уровней AI-экономики — Жаслан Мадиев Казинформ
Inform.kz
Общее1 мин
На Yandex Ads Conference Central Asia 2026 обсудили новые привычки покупателей и возможности для роста бизнеса
Каждый второй покупатель в регионе принимает решение о покупке под влиянием приложений, а ИИ обрабатывает уже миллионы запросов ежедневно.
Profit.kz — ИТ в Казахстане
Исследования1 мин
На Yandex Ads Conference Central Asia 2026 обсудили новые привычки покупателей и возможности для роста бизнеса
Каждый второй покупатель в регионе принимает решение о покупке под влиянием приложений, а ИИ обрабатывает уже миллионы запросов ежедневно.
Profit.kz — ИТ в Казахстане
Политика и регулирование1 мин
NVIDIA и General Atlantic заинтересовались «Долиной ЦОДов» в Экибастузе
🤝 NVIDIA и General Atlantic заинтересовались «Долиной ЦОДов» в Экибастузе Сразу две крупные международные компании обозначили интерес к проекту «Долина ЦОДов» в Экибастузе. NVIDIA планирует участвовать в следующем этапе проекта, а инвестиционная компания General Atlantic…
Telegram — BlueScreen.kz
Общее1 мин
Tibo только что объявил хорошую новость для платных пользователей ChatGPT.
Tibo только что объявил хорошую новость для платных пользователей ChatGPT. Все платные аккаунты ChatGPT по всему миру получат единый сброс лимитов уже сегодня. В первые два дня после запуска GPT-6.1 Sol модель сильно замедлилась из-за очень высокой нагрузки, но сейчас скорость…
Telegram — Вайб-кодинг
Политика и регулирование1 мин
Токаев предложил запустить AI Challenge для решения реальных задач экономики
💡 Токаев предложил запустить AI Challenge для решения реальных задач экономики Президент Касым-Жомарт Токаев на открытии AI & Digital Bridge 2026 предложил сформировать перечень реальных задач казахстанской промышленности, которые можно решать с помощью искусственного…
Telegram — BlueScreen.kz
Hugging Face Blog
Исследования1 мин
Robust Is Salient: An Informed Adversary Moves the Optimal Signal onto the Salience Pole
When an informed adversary shares the audience of a constrained signalling channel, the signal that best protects the truth is the signal that best describes it. On 108 confirmatory items, the adversary-robust optimum aligns exactly with the salience pole from prior work. Across…
arXiv — cs.AI
Исследования1 мин
Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying
Building automation systems are increasingly represented as semantic knowledge graphs (KGs) using ontologies such as Brick and ASHRAE 223P, creating a machine-readable substrate for artificial-intelligence applications. One promising application is translating natural-language…
arXiv — cs.AI
Исследования1 мин
Mathematical Transfer in LLMs Follows Reasoning Approach More Than Topic
When selecting mathematical training data for LLMs, a natural organizing principle is topic: probability examples for probability targets. An alternative is reasoning approach: worked solutions that share a solution method with the target, even when the mathematical domain…
arXiv — cs.AI
Исследования1 мин
ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call Repair
Structured tool calls often fail after only a small number of fields violate a schema or an execution contract. Regenerating the complete object enlarges the action surface and makes repeated repair difficult to audit. We introduce ContractRL, a contract-constrained sequential…
arXiv — cs.AI
Исследования1 мин
What Should an Agent Remember? Disentangling Retention from Retrieval in Bounded-Memory Evaluation
A persistent agent must decide both what to retain as information arrives and what to surface once a query appears, yet memory evaluations can confound these decisions by comparing methods that differ in both retention and selection. We build a streaming-recall benchmark…
arXiv — cs.AI
Исследования1 мин
EviGraph: Proof-Carrying Selective Recommendation over Temporal Public-Service Knowledge Graphs
Public-service recommendations require evidence that matches the requested service, scope, and date. Yet treating every missing detail as decisive can withhold useful recommendations. We introduce EviGraph, which distinguishes critical decision requirements from information that…
arXiv — cs.AI
Исследования1 мин
Conflicting Supervision Moves Commitment, Not Capability: A 12.29{\sigma} arrangement effect that is exactly zero under a convention-agnostic score
"Train a model on the same problems written under two incompatible conventions, both correct, and ask what the ordering of that data writes into the parameters. The learning-rate schedule is not a background condition for that question. It is the averaging operator, and it…
arXiv — cs.AI
Исследования1 мин
Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents
How should an embodied agent respond when a person's correction may be wrong? We formulate grounded correction arbitration as a choice among accepting, rejecting, inspecting the world, and asking the speaker. GAVA implements this interface with observation-bounded evidence,…
arXiv — cs.AI
Исследования1 мин
Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts
Research agents explain planned experiments. We measure predictive credit with paired forecasts sharing an intervention, forecaster, and outcome while varying description, matched explanation, and donor context. Five checks track commitment, delivery, predictive gain, alignment,…
arXiv — cs.AI
Исследования1 мин
Rules to Tools: Executable Checks for LLM Agents in Scientific Computing
Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise. Rules to Tools (R2T) supplies prepared executable checks of public scientific requirements. Matched SciCode repair groups share written…
arXiv — cs.AI
Исследования1 мин
Fault-Tolerant Budget Conservation in Distributed Multi-Agent Delegation
Resource limits are becoming an authorization boundary for AI agents that delegate work across concurrent and failure-prone workers. Parent-child allocation constraints, affine objects, and distributed escrow do not by themselves prevent overspend when replies are lost, effects…
arXiv — cs.AI
Исследования1 мин
JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretion
A sound judgment applies the law to established facts and weighs the circumstances in which they arose. However, existing methods swing between rigid statute matching and ungrounded discretion, benchmarks score a label or a rubric, and the experience that would supply the…
arXiv — cs.AI
Исследования1 мин
When Harnesses Lose the Signal: Causal Evaluation of Recovery in LLM Agents
Large language model agents rely on external harnesses to pass information between the model and its environment and to recover from execution errors. Yet recovery is usually judged only by average task success. This hides an important tension. The same operation can rescue a…
arXiv — cs.AI
Исследования1 мин
Benchmarking Prompt Optimization of Large Language Models With Chess
Evaluating large language models becomes increasingly challenging as their capabilities advance: benchmarks can saturate, public test sets risk contamination, and assessing harder tasks can require expensive grading or execution infrastructure. These challenges are amplified in…
arXiv — cs.AI
Исследования1 мин
JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces
LLM agents generate intermediate reasoning and actions token by token, making extended interactions slow and computationally expensive. Jev-style models offer fast probabilistic predictions over finite fields, but require those fields to be specified in advance. This requirement…
arXiv — cs.AI
Исследования1 мин
Heavy-Tailed Memory Traces in Long-Horizon Language Agents
Long-horizon language agents increasingly rely on external memory as a frozen world model, yet current memory systems are usually judged only by task success or token cost. We argue that the missing object is the shape of memory use: under finite context and repeated retrieval,…
arXiv — cs.AI
Исследования1 мин
When Do Causal World Models Help Modular LLM Agents
LLM agents increasingly act through modular systems, such as order, payment, inventory, and shipment services, where actions in one module change which transitions are valid in another. Standard world models usually fit observational traces, but this is not the quantity needed…
arXiv — cs.AI
Исследования1 мин
From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution
Large-language-model agents can propose and execute actions, but proposal, authority, dispatch, verified external effect, and serving promotion are different claims. We present Praxa, an agent harness that represents these states explicitly through deterministic admission,…
arXiv — cs.AI
Исследования1 мин
What Do Rationales Communicate? A Message-Intervention Study in Role-Specialized QA
Role-specialized QA pipelines increasingly pass rationales from a reasoner to a verifier, but it is unclear what this message actually buys: better answers, stronger support assessment, or a new failure surface. We introduce a message-intervention diagnostic that fixes the…
arXiv — cs.AI
Исследования1 мин
Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell commands, writing memory, selecting tools, ranking past turns. We ask whether off-the-shelf SLMs meet…
arXiv — cs.AI
Исследования1 мин
Characterizing a Configuration Where Inference-Time PRM-Pruned Fragment Grafting Is Inert: Evidence from Three Reasoning LMs
Diversity collapse in parallel chain-of-thought has motivated inference-time interventions built on a natural design: when a process reward model (PRM) prunes a chain, its high-PRM prefix is extracted and grafted verbatim as an in-context demonstration into a still-decoding…
arXiv — cs.AI
Исследования1 мин
Gradient-Aligned Pair Selection for Personalized Preference Optimization
Personalizing large language models (LLMs) requires aligning generation behavior with user-specific preferences rather than aggregate quality. While Direct Preference Optimization (DPO) provides a stable framework for preference learning, its effectiveness in personalized…
arXiv — cs.AI