Gina Wong, Drew Prinster, Suchi Saria, Rama Chellappa, Anqi Liu: Toward Calibrated Mixture-of-Experts Under Distribution Shift https://arxiv.org/abs/2606.20544 https://arxiv.org/pdf/2606.20544 https://arxiv.org/html/2606.20544

Mathur, Sayed, Madha, Singh, Khurana, Mandloi, Kamath: How Do Instructions Shape Speech? Cross-Attention Attribution for Style-Captioned Text-to-Speech https://arxiv.org/abs/2606.20532 https://arxiv.org/pdf/2606.20532 https://arxiv.org/html/2606.20532

Md Nayem Uddin, Amir Saeidi, Eduardo Blanco, Chitta Baral: LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents https://arxiv.org/abs/2606.20529 https://arxiv.org/pdf/2606.20529 https://arxiv.org/html/2606.20529

Saimun Habib, Vaishak Belle, Fengxiang He: DeepSWIP: Quotient-WMC Counterfactuals for Neural Probabilistic Logic Programs https://arxiv.org/abs/2606.20526 https://arxiv.org/pdf/2606.20526 https://arxiv.org/html/2606.20526

Harshit Singh, Ayush Pratap Singh, Nityanand Mathur: FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS https://arxiv.org/abs/2606.20518 https://arxiv.org/pdf/2606.20518 https://arxiv.org/html/2606.20518

Maria Ivanova, Pavel Zadorozhny, Rodion Levichev, Ivan Petrov, Adamenko Pavel, Ivan Lopatin, Alexey Kutalev, Dmitrii Babaev: Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages https://arxiv.org/abs/2606.20517 https://arxiv.org/pdf/2606.20517 https://arxiv.org/html/2606.20517

Sihui Dai, Mann Patel: What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations? https://arxiv.org/abs/2606.20508 https://arxiv.org/pdf/2606.20508 https://arxiv.org/html/2606.20508

Zahra Asghari Varzaneh, Reza Khoshkangini, Pia Saldeen, Lars Johansson, Thomas Ebner: Context-Aware Hierarchical Bayesian Modeling of IVF Laboratory Environmental Conditions https://arxiv.org/abs/2606.20459 https://arxiv.org/pdf/2606.20459 https://arxiv.org/html/2606.20459

Zahra Asghari Varzaneh, Reza Khoshkangini, Thomas Ebner, Lars Johansson: Interpretable Sperm Morphology Classification via Attention-Guided Deep Learning https://arxiv.org/abs/2606.20438 https://arxiv.org/pdf/2606.20438 https://arxiv.org/html/2606.20438

Zhao, Chen, Tian, Jiang, Zhang, Yu, Jiang, Gong, Liu, Liu, Zhang, Zhou: Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe https://arxiv.org/abs/2606.20381 https://arxiv.org/pdf/2606.20381 https://arxiv.org/html/2606.20381

Yuexing Hao, Xiaomin Li: Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining https://arxiv.org/abs/2606.20363 https://arxiv.org/pdf/2606.20363 https://arxiv.org/html/2606.20363

Xijia Tao, Yihua Teng, Xinyu Fu, Ziru Liu, Kecheng Chen, Yuzhi Zhao, Suiyun Zhang, Rui Liu, Lingpeng Kong: SoftSkill: Behavioral Compression for Contextual Adaptation https://arxiv.org/abs/2606.20333 https://arxiv.org/pdf/2606.20333 https://arxiv.org/html/2606.20333

Santamato, Garavagno, Solazzi, Frisoli: Leveraging systems' non-linearity to tackle the scarcity of data in the design of Intelligent Fault Diagnosis Systems https://arxiv.org/abs/2606.20323 https://arxiv.org/pdf/2606.20323 https://arxiv.org/html/2606.20323

Shihao Ji, HongXi Li, Zihui Song, Mingyu Li: Lagrange: An Open-Vocabulary, Energy-Based Sparse Framework for Generalized End-to-End Driving https://arxiv.org/abs/2606.20274 https://arxiv.org/pdf/2606.20274 https://arxiv.org/html/2606.20274

Luyang Fang, Yingchuan Zhang, Jongchan Park, Zhaoji Wang, Ping Ma, Xiaoming Zhai: Confidence-Aware Automated Assessment of Student-Drawn Scientific Models https://arxiv.org/abs/2606.20264 https://arxiv.org/pdf/2606.20264 https://arxiv.org/html/2606.20264

Huang Peng, Jiuyang Tang, Weixin Zeng, Hao Xu, Xiang Zhao: Navigating Unreliable Parametric and Contextual Knowledge: Explicit Knowledge Conflict Resolution for LLM Inference https://arxiv.org/abs/2606.20245 https://arxiv.org/pdf/2606.20245 https://arxiv.org/html/2606.20245

Federica Filippini: A Multi-Agent system for Multi-Objective constrained optimization https://arxiv.org/abs/2606.20236 https://arxiv.org/pdf/2606.20236 https://arxiv.org/html/2606.20236

Ishanu Chattopadhyay: Thermodynamic Measure of Intelligence https://arxiv.org/abs/2606.20231 https://arxiv.org/pdf/2606.20231 https://arxiv.org/html/2606.20231

Xinyi Zheng, Ling Shi, Tianlong Yu, Yongxin Zhao, Lorenz Goette, Kailong Wang: QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation https://arxiv.org/abs/2606.20227 https://arxiv.org/pdf/2606.20227 https://arxiv.org/html/2606.20227

Alessandro Sestini, Joakim Bergdahl, Amir Baghi, Jean-Philippe Barrette-LaPierre, Florian Fuchs, Linus Gissl\'en: Augmenting Game AI with Deep Reinforcement Learning https://arxiv.org/abs/2606.20210 https://arxiv.org/pdf/2606.20210 https://arxiv.org/html/2606.20210

Guillaume Olivier Delplanque (LIG), Pierre Genev\`es (LIG), Nabil Laya\"ida (LIG,TYREX), Zephirin Faure: Beyond Accuracy: Measuring Logical Compliance of Predictive Models https://arxiv.org/abs/2606.20208 https://arxiv.org/pdf/2606.20208 https://arxiv.org/html/2606.20208

Jelena Meyer, David Garcia, Dirk U. Wulff: Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact https://arxiv.org/abs/2606.20205 https://arxiv.org/pdf/2606.20205 https://arxiv.org/html/2606.20205

Yiwei Liao, Shurui Tu, Yong Xiao, Yingyu Li, Guangming Shi: Implicit Semantic-Aware Communication Based on Hypergraph Reasoning https://arxiv.org/abs/2606.20162 https://arxiv.org/pdf/2606.20162 https://arxiv.org/html/2606.20162

Heejo Kong, Beomchul Park, Sung-Jin Kim, Seong-Whan Lee: Modularity-Free Conflict-Averse Training for Generalized PINNs https://arxiv.org/abs/2606.20156 https://arxiv.org/pdf/2606.20156 https://arxiv.org/html/2606.20156

Nithyanantham, Kujat, Sesterhenn, Telgmann, J\onnigs, L\"udtke, Bartelt: BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling https://arxiv.org/abs/2606.20146 https://arxiv.org/pdf/2606.20146 https://arxiv.org/html/2606.20146

Ant\'on Asla Manz\'arraga: RACL: Reasoning-Agent Control Layers for Continuous Metaheuristic Learning https://arxiv.org/abs/2606.20142 https://arxiv.org/pdf/2606.20142 https://arxiv.org/html/2606.20142

Po-Chin Chang, Nicholas Hogan, Aske Plaat, Michiel T. van der Meer: Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring https://arxiv.org/abs/2606.20138 https://arxiv.org/pdf/2606.20138 https://arxiv.org/html/2606.20138

Yang, Jiang, Xiao, Zhang, Fang, Wan, Song, Liu, Huang, Chu, Zhao, Wang: ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research https://arxiv.org/abs/2606.20122 https://arxiv.org/pdf/2606.20122 https://arxiv.org/html/2606.20122

Kianoush Aqabakee, Leonardo Stella: Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manu... https://arxiv.org/abs/2606.20087 https://arxiv.org/pdf/2606.20087 https://arxiv.org/html/2606.20087

Zhuo Cao, Lena Krieger, Fernanda Nader, Xuan Zhao, Hanno Scharr, Ira Assent: Residual-Space Evolutionary Optimization via Flow-based Generative Models https://arxiv.org/abs/2606.20084 https://arxiv.org/pdf/2606.20084 https://arxiv.org/html/2606.20084

Minsu Kim, Se-Young Yun: Process-Verified Reinforcement Learning for Theorem Proving via Lean https://arxiv.org/abs/2606.20068 https://arxiv.org/pdf/2606.20068 https://arxiv.org/html/2606.20068

Harsh Rao Dhanyamraju, Leonidas Raghav, Aaron Lee: Autonomous Event-Driven Multi-Agent Orchestration for Enterprise AI at Scale https://arxiv.org/abs/2606.20058 https://arxiv.org/pdf/2606.20058 https://arxiv.org/html/2606.20058

Pu Li, Zhigang Lin, Qiang Wu, Yongxuan Lv, Fei Wang, Shan You: Reward as An Agent for Embodied World Models https://arxiv.org/abs/2606.19990 https://arxiv.org/pdf/2606.19990 https://arxiv.org/html/2606.19990

Xiao, Xie, Zhang, Lin, Fu, Xue, Lu, Yang, Dai, Wang, Wu, Wang, Sastry, Goldberg, Fan, Zhu, Shi: ENPIRE: Agentic Robot Policy Self-Improvement in the Real World https://arxiv.org/abs/2606.19980 https://arxiv.org/pdf/2606.19980 https://arxiv.org/html/2606.19980

Leekyeung Han, Sangwon Jung, Hyunji Min, Jinseong Jeong, Minyoung Kim, Paul Hongsuck Seo: Advancing DialNav through Automatic Embodied Dialog Augmentation https://arxiv.org/abs/2606.19948 https://arxiv.org/pdf/2606.19948 https://arxiv.org/html/2606.19948

Zhangzhao Liang, Xiaofen Xing, Mingyue Yang, Wenlve Zhou, Xiangmin Xu: PhysDrift: Bridging the Embodiment Gap in Humanoid Co-Speech Motion Generation https://arxiv.org/abs/2606.19935 https://arxiv.org/pdf/2606.19935 https://arxiv.org/html/2606.19935

Aritra Sarkar: The Tao of Agency: Autotelic AI, Embedded Agency and Dissolution of the Self https://arxiv.org/abs/2606.19924 https://arxiv.org/pdf/2606.19924 https://arxiv.org/html/2606.19924

Shengbiao Lu, Xiaodong Wei: eCNNTO: A Highly Generalizable ConvNet for Accelerating Topology Optimization https://arxiv.org/abs/2606.19921 https://arxiv.org/pdf/2606.19921 https://arxiv.org/html/2606.19921

To Eun Kim, Xuhong He, Dishank Jain, Ambuj Agrawal, Negar Arabzadeh, Fernando Diaz: Multi-Agent Transactive Memory https://arxiv.org/abs/2606.19911 https://arxiv.org/pdf/2606.19911 https://arxiv.org/html/2606.19911

Yu, Liu, Yu, Wang, Zheng, Deng, Li: MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments https://arxiv.org/abs/2606.19893 https://arxiv.org/pdf/2606.19893 https://arxiv.org/html/2606.19893

Jiayi Wang, Xu-Yao Zhang: A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models https://arxiv.org/abs/2606.19868 https://arxiv.org/pdf/2606.19868 https://arxiv.org/html/2606.19868

Kim, Ron, Singh, Moogi, Gajjar, Koduri, Hong, Shah: TelcoAgent: A Scalable 5G Multi-KPM Forecasting With 3GPP-Grounded Explainability https://arxiv.org/abs/2606.19821 https://arxiv.org/pdf/2606.19821 https://arxiv.org/html/2606.19821

Anushree Sinha, Srivaths Ranganathan, Abhishek Dharmaratnakar, Debanshu Das: Human-on-the-Loop Orchestration for AI-Assisted Legal Discovery https://arxiv.org/abs/2606.19812 https://arxiv.org/pdf/2606.19812 https://arxiv.org/html/2606.19812

Sajib Acharjee Dip, Dawei Zhou, Liqing Zhang: Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning https://arxiv.org/abs/2606.19808 https://arxiv.org/pdf/2606.19808 https://arxiv.org/html/2606.19808

Yuxu Zhou, Ond\v{r}ej Ku\v{z}elka, Yuyi Wang, Yuanhong Wang, Yi Chang: CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models https://arxiv.org/abs/2606.19788 https://arxiv.org/pdf/2606.19788 https://arxiv.org/html/2606.19788

Jiajun Li, Mingshu Cai, Yixuan Li, Yu Ding, Ran Hou, Guanyu Nie, Xiongwei Han, Wanyuan Wang: ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End? https://arxiv.org/abs/2606.19787 https://arxiv.org/pdf/2606.19787 https://arxiv.org/html/2606.19787

Aravind Narayanan, Shaina Raza: AgentFinVQA: A Deployable Multi-Agent Pipeline for Auditable Financial Chart QA https://arxiv.org/abs/2606.19782 https://arxiv.org/pdf/2606.19782 https://arxiv.org/html/2606.19782

Xuanzhi Feng, Zhengyang Li, Zeyu Liu, Haoxi Li, Yuming Jiang, Bing Guo, Jingcai Guo, Jie Zhang, Song Guo: Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning https://arxiv.org/abs/2606.19771 https://arxiv.org/pdf/2606.19771 https://arxiv.org/html/2606.19771

Rohit Negi, Mustafa Yilmaz: Optimal Scheduling in a Question-Answering Forum of Knowledge Workers https://arxiv.org/abs/2606.19759 https://arxiv.org/pdf/2606.19759 https://arxiv.org/html/2606.19759

Marty O'Neill: Grounded Inference: Principles for Deterministically Encapsulated Generative Models https://arxiv.org/abs/2606.19753 https://arxiv.org/pdf/2606.19753 https://arxiv.org/html/2606.19753