AI资讯日报 - 2026/1/11

👨‍🔬 Shih-Yang Liu, Xin Dong, Ximing Lu, Shizhe Diao, Peter Belcak, Mingjie Liu, Min-Hung Chen, Hongxu Yin, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Yejin Choi, Jan Kautz, Pavlo Molchanov

Internal Representations as Indicators of Hallucinations in Agent Tool Selection

学术论文 ArXiv 重要度: 9

利用LLM内部表征实时检测工具调用幻觉，准确率达86.4%，计算开销低，提升智能体可靠性。

👨‍🔬 Kait Healy, Bharathi Srinivasan, Visakh Madathil, Jing Wu

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

学术论文 ArXiv 重要度: 8

通过机制分析识别导致VLM提示诱导幻觉的注意力头，消融可减少40%以上幻觉，无需额外训练。

👨‍🔬 William Rudman, Michal Golovanevsky, Dana Arad, Yonatan Belinkov, Ritambhara Singh, Carsten Eickhoff, Kyle Mahowald

Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop

学术论文 ArXiv 重要度: 8

研究LLM在自消耗循环中的偏差演化，提出基于奖励的拒绝采样策略以减轻偏差，提升系统可信度。

👨‍🔬 Yaxuan Wang, Zhongteng Cai, Yujia Bao, Xueru Zhang, Yang Liu

SimuAgent: An LLM-Based Simulink Modeling Assistant Enhanced with Reinforcement Learning

学术论文 ArXiv 重要度: 8

推出SimuAgent，基于LLM的Simulink建模助手，采用ReGRPO强化学习，在5300项任务中表现优异。

👨‍🔬 Yanchang Liang, Xiaowei Zhao

RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation

学术论文 ArXiv 重要度: 7

提出视觉身份提示方法，生成多视角连贯视频以增强机器人操作数据，提升策略模型性能。

👨‍🔬 Boyang Wang, Haoran Zhang, Shujie Zhang, Jinkun Hao, Mingda Jia, Qi Lv, Yucheng Mao, Zhaoyang Lyu, Jia Zeng, Xudong Xu, Jiangmiao Pang

FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts

学术论文 ArXiv 重要度: 7

提出FaST框架，基于MoE实现大规模时空图的长时程预测，兼顾预测精度与计算效率。

👨‍🔬 Yiji Zhao, Zihao Zhong, Ao Wang, Haomin Wen, Ming Jin, Yuxuan Liang, Huaiyu Wan, Hao Wu

Learning Latent Action World Models In The Wild

学术论文 ArXiv 重要度: 6

研究从野外视频中学习潜在动作世界模型，探索连续约束潜在动作以捕获复杂行为，支持规划任务。

👨‍🔬 Quentin Garrido, Tushar Nagarajan, Basile Terver, Nicolas Ballas, Yann LeCun, Michael Rabbat

CAOS: Conformal Aggregation of One-Shot Predictors

学术论文 ArXiv 重要度: 6

提出CAOS框架，聚合多个单样本预测器并进行留一法校准，在有限数据下提供可靠的不确定性量化。

👨‍🔬 Maja Waldron

MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents

学术论文 ArXiv 重要度: 5

推出MineNPC-Task基准，用于评估《我的世界》中具备记忆能力的LLM智能体，包含216项子任务。

👨‍🔬 Tamil Sudaravan Mohan Doss, Michael Xu, Sudha Rao, Andrew D. Wilson, Balasaravanan Thoravi Kumaravel

Stock Market Price Prediction using Neural Prophet with Deep Neural Network

学术论文 ArXiv 重要度: 4

提出NP-DNN模型预测股价，结合Neural Prophet与MLP，准确率达99.21%，优于现有方法。

👨‍🔬 Navin Chhibber, Suneel Khemka, Navneet Kumar Tyagi, Rohit Tewari, Bireswar Banerjee, Piyush Ranjan

🤖 AI资讯日报

📊 今日趋势总结

Why Boring Businesses Outlast AI Hype Cycles

Ask HN: What's the pain using current AI algorithms?

Ask HN: Anyone concerned about NYC Local Law 144?

NLP, AI, ML, bots – a passing trend or much more? What's your take on this?

Ask HN: Is the rate of progress in AI exponential?

Ask HN: What would you read to learn about "artificial intelligence"?

Common Lisp + Machine Learning Internship at Google (Mountain View, CA)

The AI Crackpot Index

The Next Bill Gates or Albert Einstein in AI “Chris Clark” – Yourobot

MIT Non-AI License

Show HN: Startup Raising capital through Book Sales

Bioinformatician

Robust Reasoning as a Symmetry-Protected Topological Phase

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Internal Representations as Indicators of Hallucinations in Agent Tool Selection

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop

SimuAgent: An LLM-Based Simulink Modeling Assistant Enhanced with Reinforcement Learning

RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation

FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts

Learning Latent Action World Models In The Wild

CAOS: Conformal Aggregation of One-Shot Predictors

MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents

Stock Market Price Prediction using Neural Prophet with Deep Neural Network

📅 历史日报目录