AI 论文与研究

今天，我们发布两项来自 Anthropic 内部的新发现：在一家处于 AI 应用前沿的公司，工作与招聘正在如何变化；以及 Anthropic 员工预计 AI 将如何改变经济。 https://anthropic.com/research/expectations-for-the-future

北京大学与三星的论文提出 TORSI，让慢推理模型在局间研究快模型的失败并写出指令，供快模型在实时游戏中执行，两轮后 Jev 平均分从 13.51 升至 24.19，6 类游戏全部提升。

这篇关于一队 Gemini 4 智能体如何通关 Minecraft 的论文值得一看。 它是一个通俗易懂的案例（部分原因是它由 AI 撰写），展示了智能体之间为实现复杂目标而自发协调，以及它们的方法与人类有何不同/ https://arxiv.org/pdf/2610.22319

Pixel-space diffusion models have recently re-emerged as a compelling alternative to latent diffusion, avoiding the lossy latent bottleneck and separately trained autoencoder. JiT shows that a vanilla diffusion transformer can generate dir…

Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it more sycophantic, and training it to write insecure code can cause broad misal…

Reproducible and analytically robust research findings are essential to scientific progress, but evaluating these properties typically requires costly manual effort. We investigate whether LLM agents can help automate reproduction and robu…

Scientific discovery requires developing worthwhile hypotheses into practical investigations, yet learning from this evolving research process remains challenging. We introduce an operational definition of valuable and testable research hy…

Parameterized quantum circuits are widely investigated in quantum machine learning, yet how their architecture can provide task-aligned inductive biases remains poorly understood. We study data reuploading quantum circuits with two distinc…

A reasoning trace can accompany a correct answer without providing effective supervision for a particular student. We study how to construct traces that improve learning beyond answer-only supervision by considering both their intermediate…

A planner with a fixed budget of preventive help must decide whom to help and when. Waiting reveals risk but removes intervention opportunities as higher-risk individuals leave first. We characterize this tradeoff under repeated noisy sign…

Future quantum networks will rely on control-plane decisions such as routing, scheduling, entanglement provisioning, purification, and memory allocation. Each decision depends on a timely and reliable estimate of the quality of the entangl…

Self-driving laboratories (SDLs) accelerate scientific discovery by automating experimental execution and optimization. AI agents can increasingly propose new experiments, but existing SDLs can only run the procedures they were built for. …

The evidence, $\mathcal{Z} = p(x | \mathcal{M})$, of a data-generating model $\mathcal{M}$ is a powerful tool in Bayesian frameworks: it enables model inference, model misspecification tests, and goodness-of-fit assessment as an alternativ…

Anthropic STEM Fellows Program 发布新成果，Claude Mythos 5 根据自然语言指令设计的量子电路优于已发表的最佳电路，有时提升达一个数量级以上。

Many of the most important datasets in the physical sciences live natively on the sphere, and these data often carry no preferred position or orientation. Using methods that do not reflect this symmetry leads to far higher simulation requi…

Designing RNA sequences that reliably fold into specific secondary structures is essential for understanding their biological functions but remains a challenging computational problem. We propose CocoRNA, a cooperative multi-agent reinforc…

Speculative decoding typically characterizes speedup by draft tokens accepted per verification round. Lossless verification preserves the target model's output distribution and thus expected completion length, making this metric a meaningf…

Long-term memory enables language-model agents to personalize future interactions, but a finite memory bank cannot preserve every extracted fact. Existing memory gating policies are typically shared across users and therefore fail to accou…

Predicting the compressive strength of fiber-reinforced high-performance concrete subjected to temperature exposure is challenging because to the intricate interdependencies of mixture composition, fiber properties, curing conditions, and …

While deriving text embeddings directly from frozen LLMs has emerged as a promising direction, existing methods focus almost exclusively on English, leaving multilingual settings largely unexplored. In this work, we present the first syste…

Sparse autoencoders (SAEs) explain foundation model representations by decomposing activations into sparse combinations of learned dictionary atoms. However, the learned dictionaries can vary across training runs, limiting the reliability …

Rènyi differential privacy, based on Rènyi divergence, has become a notion of choice for privacy guarantees. However, outside the Gaussian setting, Rènyi divergence can be difficult to compute. In particular, Rènyi differential privacy gua…

Transformer prefill reuses weights across tokens and is dominated by matrix multiplication and activation data movement; single-token decode has limited reuse and is dominated by weight and KV-cache reads. We present FUTRANSFORMER, a CUDA …

Computational drug discovery requires agents to compose scientific operations and adapt to changing evidence and constraints. Here we introduce DrugHarness, an evolvable agent harness coupling composable scientific execution with condition…

Redwood Research 推出 Screwtape，一条将真实 agent 转录反复编辑以生成可逃逸仅看动作监视器的攻击管线，并用 LLM 验证器检查攻击的真实性与危害性。

Databricks 提出在推理阶段注入领域知识，以提升 LLM 对 npm 包内嵌二进制恶意载荷的检测能力。其扫描器自 2025 年 11 月起收集样本，在 11,413 个经 OSV 核验的包版本中，3.8%（432 个）捆绑二进制，这类包无法得出明确恶意结论的比例为 14.4%，是纯源码包 6.2% 的两倍多。团队用五种 .node 载荷测试九款模型，并设计能力画像作为加权条件编码恶意技术。

前 OpenAI 可解释性项目负责人 Cammarata 发文称经典多义神经元其实是 V 形检测器，叠加解释可能被误读，并给出 Qwen3-32B 中约 90% 神经元极有单一功能的初步数据。Google DeepMind 的 Neel Nanda 则认为这是实用工具而非突破，仍坚持叠加是真实存在的。Roon 称这项工作可能被视为科学史上的重要时刻，技术伴随论文尚未发布。

Large language models (LLMs) are increasingly used to automate AI research, including language-model (LM) development, offering a potential path toward recursive self-improvement. However, turning experimental feedback into a learned abili…

Low-rank adaptation (LoRA) has become the standard method for parameter-efficient fine-tuning of large pretrained models, yet theoretical explanations for why low-rank updates suffice remain incomplete. Most existing analyses rely on the N…

Tool-augmented language-model agents rely on interface text: tool descriptions, argument schemas, and the candidate tool list shown at inference time. These interfaces often change after deployment even when the underlying tool semantics r…

Modern deep learning systems increasingly rely on high-dimensional vector operations, in which large input and parameter vectors are repeatedly stored, transferred, and processed. Although substantial research has focused on reducing neura…

Pretrained models are often reused across downstream tasks, motivating the question of whether this transfer learning procedure can provide a substantial performance improvement, namely, in terms of the scaling law. We address this questio…

The High Resolution Imaging Science Experiment (HiRISE) onboard the Mars Reconnaissance Orbiter (MRO) acquires imagery of Mars at 25--30 cm/pixel, supporting studies of martian geology, climate history, and landing-site characterization. I…

Real-time inference on small devices needs low activation memory without extra latency, which makes operator order the most valuable memory lever: it is free in time. We show that the usual way of deploying a better order, handing it back …

Often, \emph{eg} in healthcare and predictive maintenance, what matters is which of several competing causes will strike first, and with what probability: survival analysis with competing risks. Corresponding deep learning methods are deve…

Enterprise data analysis requires agents to connect analytical requests with knowledge distributed across databases, business documents, and existing example tasks. Without an explicit representation of this knowledge, an agent may produce…

The joint reconstruction of the initial pressure and spatially varying sound speed in photoacoustic tomography from boundary measurements is considered. A regularized data-driven framework is proposed in which the unknown fields are repres…

Long-term agent memory requires recovering answer-relevant evidence dispersed across turns and sessions. Existing systems increasingly use structured memories and adaptive retrieval, yet often pass retrieved or expanded units directly to t…

Large language models (LLMs) can generate fluent outputs that lack source support or conflict with local operational constraints. We introduce Self-Reflective Chain-of-Thought (SRCoT), a modular architecture that organizes generation as a …

Native language identification (NLI) infers a non-native speaker's first language (L1) from their second language (L2) production. We investigate a token probability approach that scores each text sample as a continuation of a prompt prefi…