模型与评测

GPT-6 选型与生产工作流指南

Learn how startups can choose GPT-6 models, tune reasoning effort, improve prompts and skills, coordinate tools, and prepare workflows for production.

Chatham 用 Codex 与 GPT-5.6 重做交易校验

Chatham Financial uses Codex and GPT-5.6 to build technology and redesign workflows, cutting trade validation from 30 minutes to under 4.

Blackwell 加速 GPT-6 Astra Ultrafast

GPT-6 Astra Ultrafast 现已在 OpenAI API 及符合条件的 ChatGPT Work 和 Codex 用户中可用，运行在 NVIDIA Blackwell GPU 上。

Apple Pass Designer

Suncatcher 原型卫星进入轨道

A Living Benchmark for Information Retrieval from Electronic Health Records

arXiv:2609.30205v2 Announce Type: replace Abstract: Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve and synthesize information from patient records. Their safe

A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined

arXiv:2610.01938v1 Announce Type: cross Abstract: Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integrating and updating evidence across time and sources to form, revise and justify a

DGX Spark 推出 64GB 版本

NVIDIA 宣布 DGX Spark 推出 64GB 统一内存新配置，10 月 23 日起由 Acer、ASUS、Dell、Gigabyte、HP 和 MSI 发售，起步价 $4,999，支持最高 1000 亿参数模型在端侧运行。

Expanding AI Storage Access with NVIDIA cuObject and the NVIDIA SCADA Server SDK

AI infrastructure engineers, storage developers, and cloud service providers need fast and secure access to high-capacity file and object storage to support AI workloads. AI workloads increasingly require high-speed data access for training, fine-tuning, inference context, tool c

Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection

arXiv:2610.00685v1 Announce Type: new Abstract: With the rapid adoption of large language models (LLMs) and parameter-efficient fine-tuning (PEFT) methods, the risk of backdoor attacks has become more severe. Existing backdoor purification methods typically rely on at least one o

CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning

arXiv:2610.02039v1 Announce Type: cross Abstract: Recent years have witnessed the rapid adoption of reinforcement learning (RL) in large language model (LLM) post-training, with substantial gains in mathematical reasoning and code generation. In practical systems, however, policy

Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning

arXiv:2610.00562v1 Announce Type: cross Abstract: Longitudinal clinical reasoning requires large language models (LLMs) to identify and integrate relevant evidence distributed across extended patient histories. Although long-context models can process increasingly large amounts o

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

arXiv:2609.32353v2 Announce Type: replace Abstract: Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extremely low token budgets. Existing work has explored both visual-token selection an

GPEC: Efficient Pre-LLM Gaussian Process Embedding Correction for Cardiac Video Caption Generation

arXiv:2610.00196v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown strong potential for video understanding and caption generation, but their performance may decline in specialized medical imaging domains such as echocardiography. This work introd

LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery

arXiv:2610.00675v1 Announce Type: cross Abstract: Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from other experiments, whereas including the full exp

Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?

arXiv:2610.00025v1 Announce Type: new Abstract: 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

MemFit: Efficient Long-Term Agentic Memory

arXiv:2610.00872v1 Announce Type: new Abstract: Long-term memory systems for large language models (LLMs) have gained popularity for extending reasoning capabilities across applications. Current memory systems rely on LLM agents to organize and consolidate memory, resulting in co

OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation

arXiv:2610.01497v1 Announce Type: new Abstract: Molecular tumor boards integrate genomic findings, clinical context, and therapeutic evidence to support precision oncology. As AI enters this workflow, a key safety challenge is distinguishing truly unsupported recommendations from

Proof-Gated Signing: Solver-Checked Transaction Guards that Hold Under State Drift for Onchain AI Agents

arXiv:2610.00354v1 Announce Type: cross Abstract: AI agents that control wallets read attacker-reachable content, so they can be steered into proposing harmful transactions. The usual last line of defense is a pre-signing check: a static allowlist, an LLM reviewer, or a transacti

RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation

arXiv:2610.00979v1 Announce Type: new Abstract: Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data-selection strategies often allocate training at the environ

Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents

arXiv:2610.00400v1 Announce Type: cross Abstract: Multi-turn attacks on agentic systems can compose individually permissible actions into harmful outcomes, challenging defenses that assess actions or states in isolation. We show that such attacks leave a detectable signature in t

SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning

arXiv:2610.00838v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) trains a large language model (LLM) to act over long, multi-step interactions. However, a single localized error can cause task failure, while trajectory-level rewards provide limited guidance f

Scaling Clinical Judgment to Evaluate Medical AI

arXiv:2609.12822v2 Announce Type: replace Abstract: Blinded physician evaluation has been considered by many to be the gold standard for assessing clinical reasoning in large language models (LLMs). This is difficult to scale; thus, prior studies typically rely on small physician

SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses

arXiv:2609.23889v3 Announce Type: replace-cross Abstract: Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but still lacks an effective and efficient solution. The core challenge is twofold: a reproducer must first