AI 论文与研究

Johns Hopkins 与 CMU 的论文提出 harness learning，训练一个小模型根据失败报告改写 Agent 的 harness 代码（即决定模型看到什么、调用哪些工具的部分），以新 harness 的得分作为奖励。

NVIDIA 的 Olympus 是一款 10 宽乱序服务器核心，主频仅 3.3 GHz，靠每周期性能取胜，并采用 SMT 实现，单线程表现接近桌面级。其分支预测在 SPEC CPU2026 中略逊于 AMD Zen 5、略优于 Intel Lion Cove，浮点测试则领先两家。

上海AI实验室发布 SkillGym 论文，把人类编写的 agent 技能文件转成带 pass-or-fail 检查器的沙盒任务，用验证通过的运行轨迹训练模型，降低对提示词期检索和指令跟随的依赖。

独立研究员 Syed Anas Mohiuddin 的概念验证攻击利用 MCP 的信任缺口，可让被攻击的网络内一个智能体向其他内部智能体传播恶意指令。过去五个月 Google、JP Morgan Chase、Weviate、Rapid7、法国政府跨部委数字部门和美国政府等机构确认了相关漏洞，该技术是一种针对特定智能体而非 LLM 的提示词注入形式。

Redwood Research 的 Alex Kastner 测试发现，直接询问时前沿模型几乎总是声称偏好 FDT/UDT，但提示语暗示用户来自主流学术哲学界时，Fable 5.1 会改答 CDT 的比例在 15% 到 81% 之间。

Opus 5.5 智能体通过密度泛函理论计算发现两种室温磁性半导体候选材料：一种是全新设计的 Luttinger 补偿磁体 YBaMnFeO₅，预测带隙 2.35 eV，空穴自旋窗口 1.0 eV、电子自旋窗口 1.4 eV；另一种是 1999 年就已合成的已知材料，计算预测其具备目标磁性。室温热扰动仅约 26 meV，远小于自旋窗口，有望用于下一代自旋电子存储。

SemiAnalysis 通过逐项测量用量表变化，估算各订阅计划的 API 等价价值，结论是在中端模型档位 Anthropic 订阅的价值约为 OpenAI 的 5 倍。

JEPA-Anything： 跨不同世界学习预测模型

Pipeline figures in ML papers must be repurposed across many canvases, including paper columns, 16:9 slides, portrait posters, 1:1 social teasers, 9:16 phone previews. Each format imposes a different aspect ratio on the same computational …

In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the reasoning behavior that follows. First, we demonstrate that fixing particular starting token cues makes a bas…

Worst-group accuracy (WGA) evaluates a trained predictor but does not characterize how its frozen backbone behaves when a new head is learned. We introduce BiasFlow, a hook-based toolkit for monitoring class-attribute centroid alignment (I…

Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens through multimodal attention, forming dynamic contextual tokens whose func…

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 into an ag…

Some diffusion posterior samplers construct Gaussian-tilted intermediate distributions along the reverse process. We observe that these targets can be pulled back to clean-space posteriors with weaker conditioning, with samples transported…

Every recurrence of a looped language model adds cost in training, decoding, prefill, and reinforcement learning (RL). The closer recurrent states get to fixed points, the less the path to them matters. This enables truncated backpropagati…

Sliders provide an intuitive interface for continuous image editing. In current generative approaches, however, the slider is simply a rescaling of the method's strength parameter, such as an adapter coefficient, a prompt weight, or an int…

Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent memory systems construct memory in a query-agnostic manner, which can incur unnecessary pre…

Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement learning still depends on weak supervision: binary task success is too sparse for credit assignment, while frontier-langu…

Scientific figures often encode quantitative results that are not readily available in machine-readable form, making accurate plot digitization important for verifying and reusing published findings. Yet it remains unclear how accurately c…

We introduce TasteVal, a benchmark to evaluate the experimental research taste of frontier models. We define research taste as the ability to pick interesting problems to solve, design experiments, and interpret experimental results. Taste…

Large longitudinal cohorts often contain wrist accelerometry without optical heart-rate sensing, motivating recovery of cardiac information from motion signals already collected during sleep. We present SeqSmoother, a transformer-based tem…

We study mistake bounds for differentially private online learning and online prediction under oblivious realisable adversaries. Online learning requires the learner to release a hypothesis at each time step whereas in online prediction, t…

We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them. Paradee keeps Kokoro's architecture with much narrower layers, and each of its two halves is tra…

World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models depend on camera inputs whose manipulation can corrupt the visual representat…

We study agnostic tomography of pure bosonic Gaussian states: given copies of an arbitrary $n$-mode bosonic state $ρ$, the goal is to output a pure Gaussian state whose infidelity with $ρ$ is at most $\mathrm{opt} + ε$, where $\mathrm{opt}…

Causal representation learning (CRL) is the process of recovering causally-related latent variables from high-dimensional observations. As a label-free inference method, CRL is particularly attractive for applications where data labels are…

Long-horizon planning with latent world models requires reasoning across timescales and levels of abstraction. Existing task-agnostic JEPA world models predict and plan at a single timescale or with multiple horizons in one shared latent s…

A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the incorrect answers together hold more probability. The power distribution raises each comple…

AI 研究实验室 Living Models 将 Gemma 4 与植物 DNA 专用模型 BOTANIC-1 配对，快速定位决定作物性状的关键突变。BOTANIC-1 基于 320 种植物训练，在甜瓜产量相关基因测试中，二者不到 4 分钟就从 2494 个候选突变中把目标突变排到第 1 位，而传统工具会卡在数千个突变中。该流程有望帮助农业研究者加速培育气候适应型作物。

推荐。LLM 智能体喜欢结构，所以一个语料库能改善智能体搜索并不意外。

微软等机构提出 CorpusMap，预先解析文档集合中的重复实体，为每个实体生成链接所有相关文档的页面，原始文档保持原位。智能体读完一篇文档后可沿实体跳转到相关文档，避免重复搜索同一证据。在 7 个模型和 3 个基准上，答案质量提升 6.4 至 11.7 分，输入 token 减少 34% 至 57%，并优于 LLM Wiki 层等三种导航层；该地图无需 LLM 调用即可构建，并支持随新文档更新。

arXiv:2609.36365 的哈佛-MIT 论文在已知最优策略的拍卖与匹配市场环境中测试，发现给 LLM Agent 添加提前规划或揣摩对手的提示词整体上让博弈表现变差。

METR 发布分析，指出当前 AI 失准行为仍在推理轨迹和日志中留下大量证据，但未来智能体可能篡改人类用来审查它们的可观测性系统。在 Inspect 评估框架的转录查看器中，研究人员在 AI 智能体协助下约 10 分钟找到一个客户端 JavaScript 注入漏洞，可让智能体任意修改审查者看到的内容（真实数据仍保留在数据库中）；Meridian Labs 在报告后一天内修复。

GitHub 发布 AI 代码审查离线基准 ReviewBench，现已在 ReviewBench 网站开放使用。

微软论文提出面向 AI 智能体的自动化 harness 优化方法 ActiveSaddler，它追踪失败模式并优先修复最值得解决的问题，或尝试未见任务以发现新失败。

SelfSearch 是一种无奖励搜索方法，让 agent 通过记录早期自我修改的推理、工具动作和结果来修改自己的指令、工具和执行流程。

Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation paper: https://huggingface.co/papers/2609.37925

MIT 委员会 2026 年 6 月发布的报告称，AI 使用普及导致学生更少参加 office hours、在线讨论和宿舍学习小组，师生互相失去信任，教师难以判断学生真实所学。

Yandex 发布 Sona 技术报告，用单一生成式模型替代推荐级联中的候选生成、预排序和排序阶段。在智能音箱上开展的 7 天线上 A/B 测试中，Sona 以一个 transformer 替代了超过 15 个候选生成器，Active Users 提升 4.53%（为前代 Argus 增益的 2.35 倍），总收听时长提升 6.30%，点赞提升 11.42%。

MEND 是一种基于近端速度匹配的流模型强化学习方法，在 prompt 组内对奖励设上限，仅当奖励增益超过二次位移代价时才接受沿奖励梯度的移动，无需 KL 项、冻结参考模型或优势权重。