Жалпы1 мин
AutoSynthData: Кәсіпорын агенттері үшін оқыту деректерін құру
ServiceNow-AI-ның Hugging Face-тегі блог жазбасы
Hugging Face Blog
Мақалалар каталогы
Барлық материалдар
Барлық жарияланған талдаулар, егеменді стек зерттеулері, экожүйе жаңалықтары және ЖИ модельдерінің шолулары.
8967
Материал
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 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
Зерттеулер1 мин
K-Dense BYOK: An Open-Source AI Research Assistant That Runs Locally and Keeps a Hash-Chained Lab Notebook
K-Dense BYOK (bring your own keys) is a free, open-source AI research assistant for scientists in any field that runs on the researcher's own computer. The researcher supplies access to a model of their choice, hosted or running locally, and the application supplies everything…
arXiv — cs.AI
Зерттеулер1 мин
Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks
Detailed profession-specific system prompts raise token use and estimated cost per response without a consistent accuracy gain. We evaluate Scientific Agents, an open-source corpus of 503 profession-specific AGENTS.md profiles, with Gemini 3.8 Flash via OpenRouter in the Pi…
arXiv — cs.AI
Зерттеулер1 мин
Comedic Fool's Gold: Reward Exploits and Countermeasures in Conversational Humor
We investigate automated rewards for training language models in conversational humor, focusing on reward exploits and countermeasures. Two approaches aim to capture understandable surprise and predicted audience amusement. Controlled tests show that an embedding-based surprise…
arXiv — cs.AI
Стартаптар1 мин
Астанадағы AI & Digital Bridge 2026: форумда не талқыланады
Digital Business бүгін форум сайтында жұмыс істейді және негізгі мәлімдемелер, мәмілелер және оқиға орнындағы түсініктер туралы сөйлесуге дайын болады.
DigitalBusiness.kz
Стартаптар1 мин
Questions: A new resource to empower young entrepreneurs
The book “Disciplined Entrepreneurship” by Bill Aulet, managing director of the Martin Trust Center for MIT Entrepreneurship and the Ethernet Inventors Professor of the Practice at the MIT Sloan School of Management, walks readers through the 24 steps of starting a venture. With…
MIT News — AI
Білім базасы1 мин
Opus 5.5 almost lost to an open-source model...
Supabase just launched their own eval, and what's crazy is that Opus 5.5 almost lost to an open-source model. But, the point of this benchmark is not to find out which model is smartest. Instead, they drop each agent into a Supabase project and give it actual jobs. Build a…
YouTube — David Ondrej (AI Agents)
Білім базасы1 мин
Day 02 | AI BUILDER SERIES | Copilot Chat vs Copilot Cowork — When to Use Which? #microsoft #copilot
Hello everyone, welcome to another episode of AI Builder. Today we will see what's the difference between Copilot Chat and Copilot Co-work and when to use which. Think of Copilot Chat as your AI conversation partner. You want to summarize email or you want to draft a response,…
YouTube — Microsoft Developer