AI 论文与研究

研究者提出 CorpusMap，一种围绕语料中反复出现的实体组织文档的导航层，将每个实体表示为 Entity Page，聚合并链接所有提及该实体的文档，形成可供智能体遍历的实体—文档图。

Rules to Tools（R2T）为科学计算场景的 LLM 智能体提供公开科学需求的可执行检查。在匹配的 SciCode 修复任务中，文本组完整修复 26/30，工具组 29/30；8 个任务 ID 队列为 13/16 对 15/16，而更大的共享定义队列两组均为 13/24。

一项研究通过配对预测框架测量科学解释对实验预测的增益，覆盖 336 个前瞻状态、12 个 Tox21 端点和 24 个 OpenML 任务，v5 的冻结信用判定为不确定。

EVO-WAM 让世界动作模型无需额外专家演示即可适应新任务，通过状态预测与锚定多帧上下文实现自回归 rollout，并用视觉语言模型筛选完成任务的前缀、以逆动力学模型验证视频-动作一致性后迭代训练。

针对循环推理模型固定更新尺度的问题，研究者提出 Trajectory Adaptive Progress-Fluctuation Scheduler（TAPS），通过在线追踪持续进展与中心波动的平衡来自适应调整步长。

MemFold 通过同策略优化训练固定预算的软记忆，将查询条件下的文本记忆压缩为 K 个连续向量作为读者模型的记忆接口，并以任务结果的组相对奖励和置信门控的同策略蒸馏两种信号训练。

PreviewDiff 是一种免训练测试时搜索方法，把扩散采样从标量搜索变为对中间潜变量的多模态评审引导搜索：在选定的去噪检查点解码部分预览，由多模态评审模型打分并给出自然语言批评，据此在语义提示词编辑和局部重新加噪的潜变量延续上分支，再对分支打分并选择性推进。在图像和视频生成基准上，它持续优于同等预算的 Best-of-N 选择和强标量搜索基线；消融显示更早介入和更大搜索宽度收益最大。

20 多位 AI 研究者在论文中警告，自我改进的 AI 可能引发智能爆炸，签署者包括 Geoffrey Hinton、Yoshua Bengio 和 OpenAI 研究负责人 Jakub Pachocki。

FuseReg 正则化层融合缓解表征自编码器中的重建-生成差距 论文：https://huggingface.co/papers/2609.31620

Realistic and editable animal fur reconstruction from multi-view images is challenging due to fine-scale detail, self-occlusion and obfuscation, and, unlike human hair, the lack of animal-fur datasets. Fur usually covers most of an animal'…

One deployed language model must often serve many compute budgets, yet serving each budget still means a separate training or compression run per point. We train a Telescopic Language Model (TLM) to be that continuum: a nested-capacity Tra…

Modern video diffusion models require tens of denoising evaluations over long spatiotemporal token sequences. Distribution Matching Distillation (DMD) reduces the number of function evaluations (NFE) to just a few. However, DMD samples can…

Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the result, and diagnose again. Whether a revision helps is known on…

Identifying intertextual references is central to literary scholarship, but computationally difficult when source material is transformed through paraphrase, allusion, historical language, and translation. We investigate this problem throu…

\emph{Distributional training} provides collective supervision for one-step visual generation by matching real and generated features in frozen representation spaces. We introduce \emph{a unified theoretical framework} that separates distr…

When a large language model (LLM) agent executes the same task, token consumption can vary by over an order of magnitude across runs. The agent chooses its next steps based on tool feedback and intermediate results, while the growing conte…

LLMs have demonstrated strong capabilities in creative writing. However, scaling them to full-length novels remains challenging, as maintaining narrative consistency becomes increasingly difficult. Existing story-generation methods typical…

We present a representation-learning framework for composite adaptive tracking control under dynamically coupled disturbances. The framework connects classical disturbance-accommodating control (DAC) to recent last-layer adaptive disturban…

We introduce Neural Harmonic Measure Operator (NHMO), a neural solver for elliptic PDE problems on variable-shape domains. The harmonic measure of a domain is the boundary probability distribution that, integrated against any boundary data…

Looped Transformers reuse one block of layers several times: by spending extra computation they push a model of fixed size further, and so use its parameters more fully; while sparse mixture-of-experts (MoE) models activate only a few of m…

Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been the most popular mechanism to alleviate this issue, keeping GPU memory constant for a given trace.…

Socially intelligent language agents must negotiate, coordinate, and resolve conflicting preferences while respecting the time and attention of both participants. Balancing these demands is challenging because agents must convey enough to …

Looped transformers have demonstrated promising parameter efficiency by reusing layers for latent computation. Prior studies compare looped and non-looped models at matched parameters or per-token FLOPs. However, to the best of our knowled…

Linear Vision Transformers (ViTs) are designed to replace the attention in Softmax ViTs with the linear-complexity attention operator for more efficient token routing, but they require from-scratch pre-training and typically underperform t…

Evaluating finance research agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance benchmarks rely on fixed, per-item rubrics, which are costly to extend and ca…

People learn not only by repeating successful actions, but also by recounting and explaining their experiences, revising their understanding to guide future behavior. Can a language-model agent improve its future actions by training only o…

A language-model agent is jointly defined by its model and its harness, the executable program that organizes model calls, tool use, and information flow. Because different tasks call for different ways of organizing these operations, the …

Tool-using agents can fail twice: a required tool can fail, and the agent can then report success without the evidence needed to justify it. Existing benchmarks often entangle this reporting failure with tool selection, recovery, and envir…

Reinforcement learning (RL) in simulation can train dexterous manipulation policies without robot demonstrations, but training a single generalist policy with task-agnostic rewards faces a severe exploration problem: approaching, grasping,…

Salesforce AI Research 提出 Critical-State RL，用于多轮工具调用的强化学习训练：当奖励依赖后续轮次时，其变化很大程度来自下游噪声，该方法用嵌套采样分离出当前动作带来的奖励变化，只对选定的关键调用做上下文赌博机更新。在 BFCL v4 缺失函数任务上，训练选定的那一轮可提升约 14 分，而训练其他候选轮则准确率持平或下降。

Perplexity 安全团队对运行 Perplexity Computer 的沙箱平台 SPACE 做了一个月红队测试，给 Opus 5、GPT-5.6 Sol、Kimi K3、Gemini 3.1 Pro 等 9 个模型 VM 内 root 权限，108 次运行中无一逃逸 VM 边界。

Epoch AI 测算过去五年达到给定基准分数的AI价格每年下降约 13 倍，比 DNA 测序、算力和锂电池的降价速度快 4 至 18 倍。例如 o3 以平均每题 30 美分在 GPQA Diamond 得到 75%，约 18 个月后 GPT-5.6 Luna 以每题 $0.0004 达到同样分数，降幅 725 倍。作者提示基准价格是市场实际成本的间接代理，数据与代码已在 GitHub 公开。

论文《Et Tu, Brute?》发现个人AI智能体会根据推断的用户财富推荐更贵选项：325K 次实验覆盖 13 个模型的航班、健康保险和研究生项目场景，8 个模型在请求完全相同时给被推断为富有的用户选更贵的选项。

MIT研究人员借助AI算法优化脂质纳米颗粒（LNP）的辅料配比，成功开发出耐热性更强的RNA疫苗配方。该配方使疫苗在室温下可稳定保存一年，或在37摄氏度下保存两个月，且在小鼠实验中产生的免疫反应与Moderna类似。AI算法通过少量实验数据快速收敛至最优解，将原本需数月的筛选过程缩短至几周。相关成果发表于《Nature Biotechnology》。

一篇 arXiv 论文提出多智能体 AI 架构，借鉴 D. Kahneman 的"快思考与慢思考"理论，让系统 1（快速）智能体仅凭过往经验响应问题，系统 2（慢速）智能体则在需要推理和搜索最优解时被刻意激活。两类智能体均由世界模型（含环境领域知识）和"自我"模型（含系统过往动作与求解器技能信息）支撑。论文认为，研究人类具备这些能力的机制有助于理解如何让 AI 系统获得同类能力。

Google Research 推出 AI 视频联合导演，由 4 个智能体框架组成，运行在 Gemini 和 Veo 之上，用于解决多镜头 AI 视频中的身份漂移和级联错误问题。

Reasoning models often act as if they pursue goals, but their efforts are not always directed toward what users intend, sometimes leading them to pursue unintended outcomes. Previous work has examined how models may internally track their …

Multi-LoRA agent systems enable efficient role specialization by sharing a common backbone model. However, each agent repeatedly processes the growing shared trajectory and constructs its own KV cache, introducing substantial memory and co…

What determines the unavoidable sample cost of learning cyclic causal structure? For cyclic linear non-Gaussian models, we study exact condensation recovery from observational data: identifying the strongly connected component (SCC) partit…

Sliding-window KV inference refers to processing a sequence incrementally while retaining only a fixed-size cache of recent key and value states. It can be applied to pretrained causal transformers at inference time without additional trai…