Large language models are trained primarily on human-generated data and feedback, yet they exhibit persistent errors arising from annotation noise, subjective preferences, and the limited expressive bandwidth of natural language. We argue that these limitations reflect structural properties of the supervision channel rather than model scale or optimization. We develop a unified theory showing that whenever the human supervision channel is not sufficient for a latent evaluation target, it acts as an information-reducing channel that induces a strictly positive excess-risk floor for any learner dominated by it. We formalize this Human-Bounded Intelligence limit and show that across six complementary frameworks (operator theory, PAC-Bayes, information theory, causal inference, category theory, and game-theoretic analyses of reinforcement learning from human feedback), non-sufficiency yields strictly positive lower bounds arising from the same structural decomposition into annotation noise, preference distortion, and semantic compression. The theory explains why scaling alone cannot eliminate persistent human-aligned errors and characterizes conditions under which auxiliary non-human signals (e.g., retrieval, program execution, tools) increase effective supervision capacity and collapse the floor by restoring information about the latent target. Experiments on real preference data, synthetic known-target tasks, and externally verifiable benchmarks confirm the predicted structural signatures: human-only supervision exhibits a persistent floor, while sufficiently informative auxiliary channels strictly reduce or eliminate excess error.
VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training
College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；Honor Device Co., Ltd（荣耀设备有限公司）；Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究院）；Shanghai Key Laboratory of Multimodal Embodied AI（上海多模态具身人工智能重点实验室）
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning
School of Computer Science, Peking University（北京大学计算机科学学院）；College of AI, Tsinghua University（清华大学人工智能学院）；Imperial College London（伦敦帝国理工学院）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs
Zhejiang University（浙江大学）；Shanghai AI Laboratory（上海人工智能实验室）；Tencent（腾讯）；Ningbo Global Innovation Center, Zhejiang University（宁波全球创新中心，浙江大学）；Zhejiang Key Laboratory of Digital-Intelligence Service Technology（浙江省数字智能服务技术重点实验室）
Counterfactual Supervision-based Information Bottleneck for Out-of-Distribution Generalization
South China University of Technology（华南理工大学）
学习不变（因果）特征的分布外（OOD）推广最近引起了广泛的关注，其中不变风险最小化（VRM）是一个值得注意的解决方案。尽管线性回归理论上有希望，但在线性分类问题中使用递归的挑战仍然存在。通过将信息瓶颈（IB）原理引入到机器学习中，IB-SVM方法已经证明了它解决这些挑战的能力。本文从两个方面进一步改进了IB-SVM。首先，我们证明了在IB-EQUIPMENT中使用的不变特征的支持重叠的关键假设对于保证OOD泛化是强有力的，并且在没有这个假设的情况下仍然有可能实现最优解。其次，我们说明了两种故障模式，IB-ESTA（和ESTA）可能会失败的学习不变的功能，并解决这样的故障，我们提出了一个\textit{Counterfactual Supervision-based Information Bottleneck (CSIB)}学习算法，可证明恢复不变的功能。通过要求反事实推理，CSIB即使在从单个环境访问数据时也能工作。在多个数据集上的实验验证了我们的理论结果。
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
University of Cambridge（剑桥大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；KU Leuven（鲁汶大学）；University of Siena（锡耶纳大学）；Babylon Health（巴比伦健康公司）；Alan Turing Institute（艾伦·图灵研究所）
Interpretable Reward Modeling with Active Concept Bottlenecks
Department of Computer Science, ETH Zurich, Zurich, Switzerland（苏黎世联邦理工学院计算机科学系）；Department of Applied Mathematics and Theoretical Physics, University of Cambridge, United Kingdom（剑桥大学应用数学与理论物理系）
Refining the Information Bottleneck via Adversarial Information Separation
Shandong Key Laboratory of Ubiquitous Intelligent Computing, University of Jinan, Shandong, China（山东智能计算关键实验室，济南大学，山东，中国）；Quan Cheng Laboratory, Jinan, China（泉城实验室，中国济南）；David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada（大卫·R·切里顿计算机科学学院，滑铁卢大学，加拿大滑铁卢）；School of Artificial Intelligence, Shandong Women’s University, Jinan, China（人工智能学院，山东女子大学，中国济南）
