模型与评测

Gemini 3.8 Live 与扩展思考版本

Dense vs. MoE Models: Active Parameters, Throughput, and When to Choose Each

How can a 30B-parameter model activate only 3B parameters per token, and still use the capacity of the larger model? Nemotron 3.5 Lightning illustrates the answer: It uses a Mixture-of-Experts (MoE) architecture that selects only a subset of its parameters for each token. There a

How NVIDIA Groq 3 LPX Deterministic Execution Drives Power-Efficient High-Interactivity Inference on NVIDIA Vera Rubin

Power is a defining constraint for AI factories. As AI workloads demand a full compute platform to serve them, each component of that platform must maximize output within the factory’s limited power budget. This makes performance per watt—rather than raw, unnormalized throughput—

ANASSA: An Agentic AI Orchestration Framework for Spatial Intelligence

arXiv:2609.14824v1 Announce Type: new Abstract: The emergence of large language models (LLMs) and large multimodal models (LMMs) has enabled a new class of agentic systems capable of integrating natural language understanding with tool-based execution. In geographic information s

AcquireBound: Runtime Authorization for Resources Acquired by AI Agents

arXiv:2609.14744v1 Announce Type: new Abstract: By acquiring compute, credentials, accounts, services, and other agents, autonomous AI agents can introduce new authority into a task. Payment, budget, OAuth, mandate, and fulfillment checks can validate transaction conditions witho

How NVIDIA NVLink 6 Delivers Multi-Layer Resiliency for AI Factories

For operators of large-scale AI factories, maximizing continuous output is essential for productivity. In massive-scale AI training, every GPU in the cluster must synchronize gradients across thousands of collective operations per second. Similarly, during inference, unplanned do

Assessing the Applicability of Existing Design Recommendations to AI Companion Design: A Multi-Method Study

arXiv:2609.14236v1 Announce Type: cross Abstract: With the rapid proliferation of large language model (LLM)-based systems, AI companions have emerged as conversational agents designed to cultivate emotional connection rather than primarily to support humans in instrumental tasks

Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability Hunting

arXiv:2609.15523v1 Announce Type: cross Abstract: Logic attack graphs grounded in scanner output provide explicit and auditable attack path reasoning LLM-based agents lack. Integrating symbolic frameworks such as MulVAL to contemporary security workflows or agentic pipelines, how

Bridging Thought and Action: Taming Long-Horizon Instability in Open-Source LLM Agents with a MetaTool-Enhanced ROS Framework

arXiv:2609.13335v1 Announce Type: cross Abstract: Large Language Models (LLMs) have enabled more natural human-robot interaction, but open-source models often exhibit unstable long-horizon reasoning and inefficient action execution when deployed in agentic robotic frameworks. Thi

CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization

arXiv:2609.15664v1 Announce Type: cross Abstract: Amid the rapid advancement of physical-world intelligence, cloud-edge collaborative large language models (LLMs) have emerged as a promising roadmap for practical LLM deployment. However, existing cloud-edge paradigms struggle to

Carbon-Aware Routing for Function Calling in Edge-Cloud LLM Systems

arXiv:2609.13559v1 Announce Type: new Abstract: Large Language Models (LLMs) with function-calling capabilities are becoming critical for modern agentic AI systems. Nevertheless, current deployments typically route inferences to powerful cloud-based models, incurring significant

Carryover Drafting: Recycling Rejected States for Speculative Decoding

arXiv:2609.14717v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept several tokens. By construction, verification computes representations for both accep

ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution

arXiv:2609.14211v1 Announce Type: cross Abstract: Scientific applications increasingly rely on high-performance computing (HPC), yet translating a scientist's high-level goal into a correct target-scale execution remains brittle and labor-intensive. Large language model (LLM) age

EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse

arXiv:2609.15161v1 Announce Type: cross Abstract: Large language model (LLM) driven multi-agent systems have shown promise in complex clinical reasoning, yet existing approaches rely on static strategies and lack persistent clinical memory, preventing self-evolving from prior dia

Grounded Adjudication of Variations across Extracted TimeLines (GAVEL): Comparing Clinical Timelines Against Their Case Reports

arXiv:2609.13475v1 Announce Type: new Abstract: Existing pipelines for clinical timeline extraction from case reports are evaluated using an expert reference and are limited by imperfect reference annotations and imprecise event alignment. We developed GAVEL, an LLM judge protoco

K-Bench: A Benchmark for LLM Unlearning in Agentic Deployments

arXiv:2609.12808v2 Announce Type: replace Abstract: Unlearning benchmarks such as TOFU and MUSE certify forgetting by reading the model's final answer, where a model that refuses to answer already counts as having forgotten. We show that this model-level certificate does not tran

K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations

arXiv:2609.15855v1 Announce Type: cross Abstract: % !TEX root = ../main.tex People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk conversations remains poorly characterised. We developed K-Bench, a clinician-calibr

WebGPU Engine Bench: Three.js vs. PlayCanvas vs. Babylon.js

Any Nix package, live in your browser

Any Nix package, live in your browser Farid Zakaria calls this his " magnum opus of Nix work", and I can see why. trynix.dev provides a qemu-wasm powered x86_64 Linux virtual machine running entirely in your browser through WebAssembly. That VM can then be booted with any Nix pac