公開日 Intent-aligned Formal Specification Synthesis via Traceable Refinement Zhe Ye, Aidan Z.H. Yang, Huangyuan Su, Zhenyu Liao, Samuel Tenka, Zhizhen Qin, Udaya Ghai, Dawn Song, Soonho Kong April 2026 arXiv | April 2026
公開日 AMID: Model-Agnostic Dataset Distillation by Adversarial Mutual Information Minimization Aoqi Wu, Junming Liu, Yuwei Zhang, Weiquan Huang, Liang Hu, Yifan Yang, Qi Zhang, Jiaxing Miao, Yuhan Tang, Zhongyuan Lai ACM Web Conference 2026 | April 2026
公開日 Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training? Wanyi Chen, Xiao Yang, Xu Yang, Tianming Sha, Qizheng Li, Zhuo Wang, Bowen Xian, Fang Kong, Weiqing Liu, Jiang Bian April 2026 arXiv | April 2026 Github
公開日 Cost-Aware Retrieval-Augmentation Reasoning Models with Adaptive Retrieval Depth Helia Hashemi, Victor Ruehle, Saravan Rajmohan 2026 The Web Conference | April 2026
公開日 The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents Xuwei Ding, S. Zhai, Linxin Song, Jia-Te Li, Taiwei Shi, Nicholas Meade, S. Reddy, Jianyin Kang, Jie-Yu Zhao ArXiv | April 2026, 巻abs/2604.10577
公開日 From Searchable to Non-Searchable: Generative AI and Information Diversity in Online Information Seeking Yulin Yu, Yizhou Li, Siddharth Suri, Scott Counts April 2026
公開日 Litmus (Re)Agent: A Benchmark and Agentic System for Predictive Evaluation of Multilingual Models Avni Mittal, Shanu Kumar, Sandipan Dandapat, Monojit Choudhury April 2026 arXiv | April 2026
公開日 Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies Avni Mittal April 2026 arXiv | April 2026
公開日 M$^star$: Every Task Deserves Its Own Memory Harness Wenbo Pan, Shujie Liu, Xiangyang Zhou, Shiwei Zhang, Wanlu Shi, Mirror Xu, Xiaohua Jia April 2026 arXiv | April 2026
公開日 SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks Tianyi Wang, Yixia Li, Long Li, Yibiao Chen, Shaohan Huang, Yun Chen, Peng Li, Yang Liu, Guanhua Chen April 2026 arXiv | April 2026