模型与评测

Vibecoding不如手写代码有趣

Atlassian与OpenAI扩大企业知识合作

Atlassian and OpenAI are expanding their partnership to connect frontier models with enterprise knowledge and help teams plan, build, and deliver work.

开放轻量的多模态嵌入模型

Mistral Large 4

AICR 1.0：可验证的GPU集群配置

GPU-accelerated Kubernetes clusters depend on compatible versions across dozens of components, each on its own release cycle: host kernels, GPU drivers, container runtimes, networking, storage, operators, and workload frameworks. A configuration that works for one service, GPU ge

Earth AI地理空间基础模型服务全球公共卫生

Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance

Large Language Models for Model-Based Robot Design

arXiv:2609.33423v2 Announce Type: replace Abstract: Large Language Models (LLMs) can contribute useful engineering knowledge to robot design, but directly generated designs may rely on implicit assumptions and provide no guarantees of feasibility or optimality. These assumptions

Recursive Video In-Context Learning for Agentic Robot

arXiv:2610.06843v1 Announce Type: cross Abstract: LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes through text memory, which records what the agent did but not how the task is done. A demonstration video shows it, but fits poorly i

AI-Decision Checkpoints for AI-Augmented Business Process Management: Framework and Educational Instantiation

arXiv:2610.06207v1 Announce Type: new Abstract: Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI agents are increasingly embedded in operational business processes. Yet Business Process Management (BPM) curricula and frameworks still largely treat artifi

Agent Behavior as Code: Efficient and Robust LLM Agents with Programmatic Specifications

arXiv:2610.04824v1 Announce Type: new Abstract: AI agents based on foundation models (FMs) have demonstrated strong capabilities to perform complex open-ended tasks. However, they face some common challenges in practice: (a) agent behavior can deviate drastically even for semanti

AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search

arXiv:2610.05586v1 Announce Type: cross Abstract: As Large Language Models (LLMs) gain tool use capabilities such as web search, they can retrieve and cross-reference public information, creating privacy risks beyond memorization. One manifestation is re-identification: linking a

AgentSpy: Making AI Agent Behavior Observable

arXiv:2610.06001v1 Announce Type: cross Abstract: AI agents built on large language models (LLMs) run shell commands, read and write files, and reach the network, typically with their user's privileges. However, what an agent does during an execution is difficult to understand: t

Agentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents

arXiv:2610.04168v1 Announce Type: new Abstract: Agentic large language model (LLM) systems are commonly implemented as an LLM in a loop with Planning, Memory, Tools, and Control Flow. This application-focused view connects agentic LLM research with deployable systems and leaves o

Anatomy of LLM Sycophancy: What a Flip Rate Hides

arXiv:2610.06522v1 Announce Type: cross Abstract: A model under pushback can correct itself, capitulate, or hold, and one flip rate counts a correction and a capitulation alike. Using SycoLens, a modular replay protocol, we test how user pressure and evaluation settings shape mea

Asynchronous Is Nearly Free for Evolution Strategies on Long-Horizon Agentic Tasks

arXiv:2610.04196v1 Announce Type: new Abstract: LLM-based long-horizon agentic post-training is often bottlenecked by rollout generation: trajectories span many interaction turns, completion times vary substantially, and synchronous update barriers leave faster workers waiting fo

CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence

arXiv:2608.18613v2 Announce Type: replace Abstract: Cyber threat intelligence (CTI) is increasingly consumed not by human analysts but by LLM agents that compose multi-step investigations at query time. The harness side of this shift has matured rapidly, but the corpus side has n

Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving

arXiv:2610.06597v1 Announce Type: new Abstract: LLM agents increasingly execute complex workflows involving multi-turn reasoning, tool use, and parallel agents. Efficient serving requires decisions that span two layers with complementary information: the agent harness understands

Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild

arXiv:2610.04921v1 Announce Type: cross Abstract: LLM-based agentic systems are emerging as a new software paradigm. Modern agents are typically composed of backbone LLMs and a surrounding harness that serves as the operational software infrastructure for agent execution. As agen

Decide, Ask, or Defer: Clinical LLMs under Incomplete Evidence

arXiv:2610.04542v1 Announce Type: new Abstract: Clinical LLMs must decide not only what diagnosis to produce, but also whether the available evidence is sufficient for autonomous decision making. Binary DECIDE/ABSTAIN formulations merge distinct non decision states and do not exp

HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention

arXiv:2610.06563v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no valid solution exists. Recent work has formalized this reliabil

IRSTD-Agent: Agentic Infrared Small Target Detection via Zoom-Guided Interaction Learning

arXiv:2610.05342v1 Announce Type: cross Abstract: Infrared small-target detection plays an important role in maritime monitoring and aerial surveillance. Although multimodal large language models (MLLMs) offer promising capabilities for visual understanding, existing MLLM-based a

Label Agreement Does Not Measure Authorization

arXiv:2610.04544v1 Announce Type: new Abstract: Many groups now delegate label ontology and metadata harmonization to agentic LLM pipelines. We built one and audited it. Our aggregate scores looked healthy, but the pipeline kept failing in ways they did not show, so we set out to

Language Model Fingerprinting Requires Rethinking Watermark Teachers

arXiv:2610.04169v1 Announce Type: cross Abstract: LLM fingerprinting via watermark distillation embeds a statistical watermark signal into model weights, enabling model owners to identify their models behind black-box APIs. Revisiting a recent protocol, we find that its utility e