Eliezer Shlomi, Ido Levy, Eilam Shapira, Michael Katz, Guy Uziel, Segev Shlomov, Nir Mashkif, Roi Reichart, Sarah Keren
备注：
40 pages, 9 figures. Code: https://github.com/embedplan/EmbedPlan . v2: revised throughout, adds reference methods from no-change baselines to symbolic action-model induction, candidate pools up to every observed state, multi-step rollout, comparisons with LLMs, a link to the public code repository, and a reader's appendix
Planning requires a transition model that predicts how each action changes the current state. When a large language model (LLM) plays this role, every next state is generated token by token, which makes searching over many possible futures slow and expensive. Existing alternatives either still query an LLM at every step or require a symbolic model of the domain. We propose EmbedPlan, a transition model built on frozen text embeddings: it embeds natural language descriptions of the state and the action with a frozen LLM, predicts the embedding of the next state with a lightweight learned network, and returns the closest real state. Because this network can be trained on top of any encoder, EmbedPlan also provides a controlled way to compare text representations for learning transitions. We evaluate it on 9 classical planning domains, under six settings that hold out progressively more of the data, from transitions to entire domains, and against baselines ranging from predicting no change to learning symbolic action rules. On planning problems seen during training, EmbedPlan almost always ranks the true next state among its top five guesses, still does so for most queries even when every observed state is a candidate, and retains 92-99% of its single-step accuracy when predicting several steps ahead from its own outputs. Given the same candidate states as GPT-5.4, it picks the true next state more often while taking about 0.17 ms per transition with cached embeddings. Accuracy is lower on unseen problems and near chance on unseen domains, and the controlled comparison traces this limit to the state representation rather than to the learned transition.
Causal Effect Estimation with Latent Textual Treatments
School of Computer Science and Engineering, The Hebrew University of Jerusalem（计算机科学与工程学院，特拉维夫大学）；Department of Economics, Stanford University（斯坦福大学经济系）；Graduate School of Business, Stanford University（斯坦福大学商学院）
Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning
Tencent BAC（腾讯BAC）；Shenzhen International Graduate School, Tsinghua University（深圳国际研究生院，清华大学）；School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；School of Mathematics and Statistics, University of Glasgow（格拉斯哥大学数学与统计学学院）
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
University of Science and Technology of China（中国科学技术大学）；Tsinghua University（清华大学）；National University of Singapore（新加坡国立大学）；Zhongguancun Academy（中关村学院）
3M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation
Artificial Intelligence Research Laboratory（人工智能研究实验室）；College of Information Sciences and Technology（信息科学与技术学院）；Center for Artificial Intelligence Foundations and Scientific Applications（人工智能基础与科学应用中心）；Institute for Computational and Data Sciences（计算与数据科学研究所）；The Pennsylvania State University（宾夕法尼亚州立大学）
Long and Diverse Text Generation with Planning-based Hierarchical Variational Model
Institute for Artificial Intelligence（人工智能研究院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；Baozun（宝尊）
