模型与评测

The Vibe Shift in Software Engineering: Evaluating AI-Led Conversational Programming for Performance, Cognition, and Responsible Adoption

arXiv:2609.09560v1 Announce Type: cross Abstract: This study evaluates Vibe Coding, an emerging AI-led conversational programming paradigm that enables developers to generate software through natural-language interaction with large language models. Using a mixed-methods design, t

How Full-Stack NIM Optimizations Deliver 2.5x More Users on Nemotron 3 Ultra

Deploying a large language model is only the first step toward production-ready serving. Production teams also need to serve as many concurrent users as possible on available GPU infrastructure while preserving the interactivity that keeps applications responsive. That tradeoff m

What if everything changes tomorrow? A Canadian company is using AI to help businesses navigate supply chain uncertainty

Tags: Customers The post What if everything changes tomorrow? A Canadian company is using AI to help businesses navigate supply chain uncertainty appeared first on Source .

Cloudera and Mistral Partner to Bring Specialized, Sovereign Intelligence to Enterprise Data

Cloudera and Mistral join forces to bring specialized, sovereign AI intelligence to enterprise data, helping regulated industries innovate on their own terms.

What algorithm did Windows XP use to choose your initial user picture?

From Wafer-Out to First Token: Codifying Supply Chain Expertise with Nemotron and Palantir Foundry

NVIDIA has one of the largest and most complex supply chains in the world, and its performance is measured from wafer-out to first token. The interval is in two parts. Time-to-rack runs from silicon leaving the fab to an assembled system arriving on a data center floor. Time-to-t

AXON: A ROS 2 RMW with Shared-Memory/QUIC Transport and QKD/ML-KEM Key Establishment

arXiv:2609.10024v1 Announce Type: new Abstract: Robot Operating System 2 (ROS 2) standardizes application code against a middleware interface (RMW) whose reference implementations are built on the Data Distribution Service (DDS). We present AXON, an alternative ROS 2 RMW implemen

Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses

arXiv:2609.05736v2 Announce Type: replace Abstract: LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state handling, and recovery logic. We study this setting as resource-bounded harnes

Context operations to architecture modelling output from large language models and evaluation criteria for their use in systems engineering design

arXiv:2609.10132v1 Announce Type: cross Abstract: The development of generative artificial intelligence resources enables opportunities of speeding up systems and engineering design work. This contribution introduces a framework of formal operations for assembling context in LLM

KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?

arXiv:2607.27231v3 Announce Type: replace Abstract: Modern AI systems depend on specialized accelerator kernels, whose development is complicated by increasingly diverse operators and hardware. LLMs and agentic systems promise to automate this work, but existing evaluations do no

Multi-Agent Agentic Graph Learning via Structural Signatures

arXiv:2609.09565v1 Announce Type: new Abstract: Agentic graph learning (AGL) has recently achieved promising results on graph reasoning tasks, where an agent powered by a large language model (LLM) sequentially samples the graph as evidence to support its final prediction. Existi

With a Thermomix You Lose the Ability to Cook: A Kitchen Machine Analogy for Applications of Generative AI in Education

arXiv:2609.09856v1 Announce Type: cross Abstract: The rapid adoption of generative AI tools such as ChatGPT has sparked intense debate about their risks and opportunities for education, as well as the ways researchers should investigate them. In this paper, we approach these disc

StreetDiff: Multi-view Street Scenes Generation via Cross-view Consistent Multi-view Stable Diffusion with Structure Prompts

arXiv:2609.09890v1 Announce Type: new Abstract: Multi-view diffusion models have shown strong performance in scenes with strong geometric priors and sparse semantics, such as indoor rooms or simple outdoor environments (e.g., fields, courtyards). However, they often fail to maint

Omni Interaction Agent Technical Report

arXiv:2609.08977v2 Announce Type: replace-cross Abstract: In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic capabilities within a single framework. In contrast to turn-based conventional paradigms, Gander continuo

3rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Sev

arXiv:2609.10187v1 Announce Type: new Abstract: In this work, we introduce language-aligned motion representations for domain-generalizable UPDRS-Gait severity estimation, aiming to learn semantically structured motion features that generalize across heterogeneous clinical domain

A-JIT: Agentic Just-In-Time Software Construction

arXiv:2609.10248v1 Announce Type: cross Abstract: Traditional software delivery assumes a static paradigm: code is constructed prior to execution and deployed as a fixed artifact. We present Agentic Just-In-Time Software Construction (A-JIT), a paradigm that replaces static binar

AgentAudit: An Open, Extensible Framework for Full-Lifecycle Trust Evaluation of AI Agents

arXiv:2609.09875v1 Announce Type: new Abstract: Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion (AgentBench) or security robustness (AgentDojo, ASB), rather than the complete pipeline of planning, tool selection, tool execution, me

Agentic AI-enabled Semantic Commissioning of a Cognitive Digital Twin for Reconfigurable Manufacturing

arXiv:2609.09503v1 Announce Type: new Abstract: Rapid bespoke commissioning of the Cognitive Digital Twin (CDT) is a major challenge in reconfigurable manufacturing. Traditional digital twin (DT) construction methods primarily focus on geometric reconstruction, often neglecting t

An Autonomous GeoAI Agent for Arctic Eco-Navigation

arXiv:2609.09374v1 Announce Type: new Abstract: Arctic maritime navigation is becoming increasingly important as changing sea-ice conditions expand seasonal accessibility while simultaneously introducing substantial operational, environmental, and community risks. Arctic route pl

An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks

arXiv:2609.09404v1 Announce Type: cross Abstract: Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services. Most of these agents also read images, which gives an attacker a way to put text into the agent's context with

Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval

arXiv:2609.10008v1 Announce Type: new Abstract: Composed video retrieval (CoVR) searches a gallery for the target video that realizes a natural-language modification of a source clip. However, at gallery scale, this creates a fundamental tension: compact embeddings enable efficie

Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery

arXiv:2609.09647v1 Announce Type: new Abstract: Agentic systems are rapidly moving to production, where they read untrusted inputs, call tools with real permissions, and act autonomously, expanding the security surface beyond chat-only models. Yet standard evaluations remain sing

CGSM: Concept-Guided Segmentation Model for Precise Pulmonary Lesion Delineation

arXiv:2609.07004v2 Announce Type: replace Abstract: Accurate segmentation of pulmonary lesions is essential for effective clinical diagnosis and treatment strategies. Existing segmentation approaches often lack task-specific semantic guidance, as text-based annotations typically

CHIMERA Challenge Task 2 and 3: Response Subtypes Classification and Progression Survival Prediction in Bladder Cancer Patients using Multimodal Datasets

arXiv:2609.09510v1 Announce Type: cross Abstract: High-risk non-muscle-invasive bladder cancer (HR-NMIBC) carries substantial risks of recurrence and progression, while current clinical risk stratification remains limited. CHIMERA was established as a multimodal AI challenge to b