Sahil Sen, Akhil Kasturi, Elias Lumer, Anmol Gulati, Vamse Kumar Subbiah: Is Grep All You Need? How Agent Harnesses Reshape Agentic Search https://arxiv.org/abs/2605.15184 https://arxiv.org/pdf/2605.15184 https://arxiv.org/html/2605.15184

Sayantan Kumar, Shahriar Noroozizadeh, Juyong Kim, Jeremy C. Weiss: Text Knows What, Tables Know When: Clinical Timeline Reconstruction via Retrieval-Augmented Multimodal Alignment https://arxiv.org/abs/2605.15168 https://arxiv.org/pdf/2605.15168 https://arxiv.org/html/2605.15168

Ryan Wei Heng Quek, Sanghyuk Lee, Alfred Wei Lun Leong, Arun Verma, Alok Prakash, Nancy F. Chen, Bryan Kian Hsiang Low, Daniela Rus, Armando Solar-Lezama: MeMo: Memory as a Model https://arxiv.org/abs/2605.15156 https://arxiv.org/pdf/2605.15156 https://arxiv.org/html/2605.15156

Laskar, Fu, Sarfjoo, McNamara, Robertson, TN: From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents https://arxiv.org/abs/2605.15104 https://arxiv.org/pdf/2605.15104 https://arxiv.org/html/2605.15104

Renning Pang, Tian Lan, Leyuan Liu, Xiaoming Huang, Piao Tong, Xiaosong Zhang: Improving Multi-turn Dialogue Consistency with Self-Recall Thinking https://arxiv.org/abs/2605.15102 https://arxiv.org/pdf/2605.15102 https://arxiv.org/html/2605.15102

Ziyin Zhang, Zihan Liao, Hang Yu, Peng Di, Rui Wang: ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World https://arxiv.org/abs/2605.15081 https://arxiv.org/pdf/2605.15081 https://arxiv.org/html/2605.15081

Guangyu Feng, Huanzhi Mao, Prabal Dutta, Joseph E. Gonzalez: Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs https://arxiv.org/abs/2605.15077 https://arxiv.org/pdf/2605.15077 https://arxiv.org/html/2605.15077

Vinicius Covas, Jorge Alberto Hidalgo Toledo: AI Knows When It's Being Watched: Functional Strategic Action and Contextual Register Modulation in Large Language Models https://arxiv.org/abs/2605.15034 https://arxiv.org/pdf/2605.15034 https://arxiv.org/html/2605.15034

Guanhua Chen, Chuyue Huang, Yutong Yao, Shudong Liu, Xueqing Song, Lidia S. Chao, Derek F. Wong: From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG https://arxiv.org/abs/2605.15019 https://arxiv.org/pdf/2605.15019 https://arxiv.org/html/2605.15019

Zihan Deng, Xiaozhen Zhong, Chuanzhi Xu: COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion https://arxiv.org/abs/2605.15016 https://arxiv.org/pdf/2605.15016 https://arxiv.org/html/2605.15016

Peter A. Jansen: The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale https://arxiv.org/abs/2605.15011 https://arxiv.org/pdf/2605.15011 https://arxiv.org/html/2605.15011

Rebecca Handler, Suhana Bedi, Nigam Shah: Quantifying and Mitigating Premature Closure in Frontier LLMs https://arxiv.org/abs/2605.15000 https://arxiv.org/pdf/2605.15000 https://arxiv.org/html/2605.15000

Jie Jiang, Xing Sun: Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing https://arxiv.org/abs/2605.14978 https://arxiv.org/pdf/2605.14978 https://arxiv.org/html/2605.14978

Guanhua Chen, Yutong Yao, Shenghe Sun, Ci-Jun Gao, Shudong Liu, Lidia S. Chao, Feng Wan, Derek F. Wong: Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA https://arxiv.org/abs/2605.14928 https://arxiv.org/pdf/2605.14928 https://arxiv.org/html/2605.14928

Volodymyr Ovcharov: Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Text: A Comparative Study https://arxiv.org/abs/2605.14890 https://arxiv.org/pdf/2605.14890 https://arxiv.org/html/2605.14890

Eric Laporte, Elsa Tolone, Mathieu Constant: Conversion of Lexicon-Grammar tables to LMF. Application to French https://arxiv.org/abs/2605.14816 https://arxiv.org/pdf/2605.14816 https://arxiv.org/html/2605.14816

Songyang Gao, Yinghui Xia, Siyi Liu, Hui Xiong: Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation https://arxiv.org/abs/2605.14790 https://arxiv.org/pdf/2605.14790 https://arxiv.org/html/2605.14790

Titouan Parcollet, Shucong Zhang, Xianrui Zheng, Rogier C. van Dalen: Streaming Speech-to-Text Translation with a SpeechLLM https://arxiv.org/abs/2605.14766 https://arxiv.org/pdf/2605.14766 https://arxiv.org/html/2605.14766

Sangwoo Kim: Non-linear Interventions on Large Language Models https://arxiv.org/abs/2605.14749 https://arxiv.org/pdf/2605.14749 https://arxiv.org/html/2605.14749

Weimin Xiong, Shuhao Gu, Bowen Ye, Zihao Yue, Lei Li, Feifan Song, Sujian Li, Hao Tian: Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining https://arxiv.org/abs/2605.14747 https://arxiv.org/pdf/2605.14747 https://arxiv.org/html/2605.14747

Jos\'e Manuel de la Chica Rodr\'iguez, Carlos Mart\'i-Gonz\'alez: Mechanical Enforcement for LLM Governance:Evidence of Governance-Task Decoupling in Financial Decision Systems https://arxiv.org/abs/2605.14744 https://arxiv.org/pdf/2605.14744 https://arxiv.org/html/2605.14744

Vicent Briva-Iglesias, Mar\'ia Ferre-Fern\'andez: AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents https://arxiv.org/abs/2605.14679 https://arxiv.org/pdf/2605.14679 https://arxiv.org/html/2605.14679

Eric Chamoun, Yizhou Chi, Yulong Chen, Rui Cao, Zifeng Ding, Michalis Korakakis, Andreas Vlachos: SciPaths: Forecasting Pathways to Scientific Discovery https://arxiv.org/abs/2605.14600 https://arxiv.org/pdf/2605.14600 https://arxiv.org/html/2605.14600

Tian, Chen, Chen, Kong, Wang, Chen, Zhao, Li, Zhao, Wang, Xiong, Yin: EndPrompt: Efficient Long-Context Extension via Terminal Anchoring https://arxiv.org/abs/2605.14589 https://arxiv.org/pdf/2605.14589 https://arxiv.org/html/2605.14589

Artem Vazhentsev, Vladislav Smirnov, David Li, Maxim Panov, Timothy Baldwin, Artem Shelmanov: Uncertainty Quantification for Large Language Diffusion Models https://arxiv.org/abs/2605.14570 https://arxiv.org/pdf/2605.14570 https://arxiv.org/html/2605.14570

Mengjie Ren, Jie Lou, Boxi Cao, Xueru Wen, Hongyu Lin, Xianpei Han, Le Sun, Xing Yu, Yaojie Lu: Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards https://arxiv.org/abs/2605.14539 https://arxiv.org/pdf/2605.14539 https://arxiv.org/html/2605.14539

ZiYi Dong, Yuliang Huang, Weijian Deng, Xiangyang Ji, Liang Lin, Pengxu Wei: Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space https://arxiv.org/abs/2605.14531 https://arxiv.org/pdf/2605.14531 https://arxiv.org/html/2605.14531

GAng Peng: Dimension-Level Intent Fidelity Evaluation for Large Language Models: Evidence from Structured Prompt Ablation https://arxiv.org/abs/2605.14517 https://arxiv.org/pdf/2605.14517 https://arxiv.org/html/2605.14517

Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang, Shiyu Chang, Yaar Harari, Evgeniy Gabrilovich: GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations https://arxiv.org/abs/2605.14498 https://arxiv.org/pdf/2605.14498 https://arxiv.org/html/2605.14498

Ji-eun Kim: Cross-Linguistic Transcription and Phonological Representation in the Hu\`it\'onggu\v{a}nx\`i Hu\'ay\'iy\`iy\v{u} https://arxiv.org/abs/2605.14480 https://arxiv.org/pdf/2605.14480 https://arxiv.org/html/2605.14480

Yihang Chen, Pin Qian, Su Wang, Sipeng Zhang, Huan Xu, Shuhuai Lin, Xinpeng Wei: Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict https://arxiv.org/abs/2605.14473 https://arxiv.org/pdf/2605.14473 https://arxiv.org/html/2605.14473

Sunil Kumar Kopparapu: A Calculus-Based Framework for Determining Vocabulary Size in End-to-End ASR https://arxiv.org/abs/2605.14427 https://arxiv.org/pdf/2605.14427 https://arxiv.org/html/2605.14427

Kyomin Hwang, Hyeonjin Kim, Sangyeon Cho, Nojun Kwak: Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation https://arxiv.org/abs/2605.14404 https://arxiv.org/pdf/2605.14404 https://arxiv.org/html/2605.14404

Shen, Zhou, Wu, Zhao, Lin, Huang, Zhong, Zhang, Zhang, Fan, Yan: Agentic Recommender System with Hierarchical Belief-State Memory https://arxiv.org/abs/2605.14401 https://arxiv.org/pdf/2605.14401 https://arxiv.org/html/2605.14401

Hoang-Thuy-Duong Vu, Quoc-Cuong Pham, Huy-Hieu Pham: Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation https://arxiv.org/abs/2605.14380 https://arxiv.org/pdf/2605.14380 https://arxiv.org/html/2605.14380

Injin Kong, Hyoungjoon Lee, Yohan Jo: Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement https://arxiv.org/abs/2605.14368 https://arxiv.org/pdf/2605.14368 https://arxiv.org/html/2605.14368

Su, Zhang, Liu, Song, Xu, Zheng, Zhang, Fu, Xu, Zhang: Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax https://arxiv.org/abs/2605.14366 https://arxiv.org/pdf/2605.14366 https://arxiv.org/html/2605.14366

Sinclair Schneider, Florian Steuber, Gabi Dreo Rodosek: LLM-based Detection of Manipulative Political Narratives https://arxiv.org/abs/2605.14354 https://arxiv.org/pdf/2605.14354 https://arxiv.org/html/2605.14354

Sinclair Schneider, Florian Steuber, Joao A. G. Schneider, Gabi Dreo Rodosek: Ideology Prediction of German Political Texts https://arxiv.org/abs/2605.14352 https://arxiv.org/pdf/2605.14352 https://arxiv.org/html/2605.14352

Xun Fang, Yunchen Li, Hang Yuan, Zhou Yu: Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding https://arxiv.org/abs/2605.14305 https://arxiv.org/pdf/2605.14305 https://arxiv.org/html/2605.14305

Chengzhi Liu, Yichen Guo, Yepeng Liu, Yuzhe Yang, Qianqi Yan, Xuandong Zhao, Wenyue Hua, Sheng Liu, Sharon Li, Yuheng Bu, Xin Eric Wang: Auditing Agent Harness Safety https://arxiv.org/abs/2605.14271 https://arxiv.org/pdf/2605.14271 https://arxiv.org/html/2605.14271

Adam Nohejl, Xuanxin Wu, Yusuke Ide, Maria Angelica Riera Machin, Yi-Ning Chang, Hitomi Yanaka: What Makes Words Hard? Sakura at BEA 2026 Shared Task on Vocabulary Difficulty Prediction https://arxiv.org/abs/2605.14257 https://arxiv.org/pdf/2605.14257 https://arxiv.org/html/2605.14257

Zhanhao Hu, Xiao Huang, Patrick Mendoza, Emad A. Alghamdi, Basel Alomair, Raluca Ada Popa, David Wagner: GradShield: Alignment Preserving Finetuning https://arxiv.org/abs/2605.14194 https://arxiv.org/pdf/2605.14194 https://arxiv.org/html/2605.14194

Kai Guo, Xinnan Dai, Zhibo Zhang, Nuohan Lin, Shenglai Zeng, Jie Ren, Haoyu Han, Jiliang Tang: Why Retrieval-Augmented Generation Fails: A Graph Perspective https://arxiv.org/abs/2605.14192 https://arxiv.org/pdf/2605.14192 https://arxiv.org/html/2605.14192

Letian Peng, Ziche Liu, Yiming Huang, Longfei Yun, Kun Zhou, Yupeng Hou, Jingbo Shang: BOOKMARKS: Efficient Active Storyline Memory for Role-playing https://arxiv.org/abs/2605.14169 https://arxiv.org/pdf/2605.14169 https://arxiv.org/html/2605.14169

Michael S. Lee, et al.: ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety https://arxiv.org/abs/2605.14152 https://arxiv.org/pdf/2605.14152 https://arxiv.org/html/2605.14152

Pablo J. Diego-Sim\'on, Pierre Orhan, Yair Lakretz, Jean-R\'emi King: Polar probe linearly decodes semantic structures from LLMs https://arxiv.org/abs/2605.14125 https://arxiv.org/pdf/2605.14125 https://arxiv.org/html/2605.14125

Lara, Milios, Luo, Sharma, Luo, Beckham, Golemo, Pal: Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards https://arxiv.org/abs/2605.14117 https://arxiv.org/pdf/2605.14117 https://arxiv.org/html/2605.14117

Yikun Han, Mengfei Lan, Halil Kilicoglu: When Evidence Conflicts: Uncertainty and Order Effects in Retrieval-Augmented Biomedical Question Answering https://arxiv.org/abs/2605.14115 https://arxiv.org/pdf/2605.14115 https://arxiv.org/html/2605.14115

Mokshit Surana, Archit Rathod, Akshaj Satishkumar: Measuring and Mitigating Toxicity in Large Language Models: A Comprehensive Replication Study https://arxiv.org/abs/2605.14087 https://arxiv.org/pdf/2605.14087 https://arxiv.org/html/2605.14087