The Who's Who of AI

“ARC has their own writeup of GPT-6 Astra's suspiciously high results, with my favorite genre of "more reasoning is cheaper" result. arcprize.org/blog/astra”

“Not a typo! Lotta caveats here it seems, but even the 62.7 score is an insane leap forward. ARC-AGI-3 is uniquely difficult. arcprize.org/blog/astra”

“InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimodal Large Language Models Chao Shen, Xinyuan Li, Yunfan Zhou, Jianguo Yao, Haibing Guan, Zhihai Wang, Xijun Li https://t.co/e8QsqSVeHF [𝚌𝚜.𝙰𝙸] https://t.co/oifnzphd2j”

“A study shows Multimodal Large Language Models struggle with gauge reading, achieving just 25.7% accuracy in task performance. The InSituMeasure benchmark highlights issues from noise and viewpoint changes, indicating a need for better training in complex c…”

“"Questionable practices" arxiv.org/abs/2407.12220”

“FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models Yalun Wu, Junfeng Fang, Jiawei Wang, Haotian Liu, Qijun Yang, … https://t.co/nxbzqpV1cV [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶] 💬Published as a conference paper at …”

“SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation Marco Cipriano, Leonardo Zini, Alexandra Schild, Valentin Teutschbein, Afsana Mimi, Marcella Cornia, Lorenzo Baraldi, Gerard de Melo https://t.co/zD542JfRau [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚅] https://t.co/vIs9wUFXRN”

“Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation Yan Tang, Tingyu Cao, Yuanbo Tang, Huaze Tang, Keer Hu https://t.co/p0WOLTaiR2 [𝚌𝚜.𝙰𝙸] https://t.co/YyJOL3cky6”

“KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents Yaxing Lyu, Shengjie Zhou, Binbin Toh, Pengyu Zhu, Lijun Li https://t.co/D6NGUMN2Dk [𝚌𝚜.𝙰𝙸] https://t.co/flZRys2aZV”

“HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews Tzu-Ling Lin, Dong-Ting Yao, Teng-Fang Hsiao, Wei-Chih Chen, Hong-Han Shuai https://t.co/RH2Sh658VK [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻] 💬Accepted to EMNLP Findings 2026 https://t.co/je…”

“GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis Linh Le, Melanie Bui, My Chiffon Nguyen, Zachary Schlosser, David Williams-King https://t.co/tKQg6qUpAW [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚈] https://t.co/Gw9goDgqW4”

“DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents Puneet Mathur, Dinesh Manocha https://t.co/YdP9x2TgbN [𝚌𝚜.𝙰𝙸] https://t.co/kywmVLJtq3”

“AI Contextual Measurement for Recovering Individual and Group-Level Effects: Validation Against Survey Measures and an Occupational Application Wenxin Jiang, Xuyang Wang, Yuxiao Wu https://t.co/MzfjSBSdr6 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶] https://t.co/Cn9Jt5kdla”

“Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents Vasileios Rizeakos, Georgios Paisios, Alexandros Machairas, Michael Birbas, Athanasios Bachoumis https://t.co/7CMHBgWeL0 [𝚌𝚜.𝙰𝙸] https://t.co/TnVAy2ZIhD”