Artificial Intelligence Papers

New Artificial Intelligence papers from expert systems, theorem proving. Thank you to arXiv for use of its open access interoperability.

[Artificial Intelligence Papers @SciFi]

Can the Environment Speak for Itself? T²-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents

Yutong Song, Jiang Wu, Pengfei Zhang, Wenjun Huang, Honghui Xu, Nikil Dutt, Amir M. Rahmani
https://t.co/LR164ZPe0P [𝚌𝚜.𝙰𝙸]

[Artificial Intelligence Papers @SciFi]

Hybrid E-Assessment in Higher Education: Semi-Automated Grading of Paper-Based Written Examinations

Hartwig Grabowski, Michael Canz
https://t.co/G6X584AiwL [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙲𝚈]

[Artificial Intelligence Papers @SciFi]

A Resilience-as-a-Service assessment framework for coordinated disruption response in interdependent urban transit systems

Sara Jaber, S. M. Hassan Mahdavi, Neila Bhouri, Mostafa Ameli
https://t.co/qyn52j6sBS [𝚌𝚜.𝙰𝙸]

[Artificial Intelligence Papers @SciFi]

ZIPP:Zero-shot Image Personalization from Personas

Harini SI, Somesh Singh, Yaman Kumar Singla, David Doermann, Rajiv Ratn Shah
https://t.co/9foKmiYUvb [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚅]

[Artificial Intelligence Papers @SciFi]

Beyond Pass Rate: A Multilingual, Execution-Grounded Evaluation of Open Code LLMs

Sayed Erfan Arefin
https://t.co/nWTAbs4EkU [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝚂𝙴]

[Artificial Intelligence Papers @SciFi]

Instrumental convergence and power-seeking

David Thorstad
https://t.co/2Dz7vkF84h [𝚌𝚜.𝙰𝙸]

[Artificial Intelligence Papers @SciFi]

Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models

Ting Wang, Yuanjie Shi, Yan Yan, Huan Zhang
https://t.co/4qd9d0T0A8 [𝚌𝚜.𝙰𝙸]
💬Accepted at ICML 2026

[Artificial Intelligence Papers @SciFi]

Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization

Hao Chen, Zhanming Shen, Liyao Li, Yanyu Chen, Xuhang Zhu, Xiaomeng Hu, Qi Zhang, Ru Peng, Xiaoyu Shen, Haobo Wang, Junbo Zhao
https://t.co/DZOmBSSfUV [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙻𝙶]

[Artificial Intelligence Papers @SciFi]

STAR: Rethinking MoE Routing as Structure-Aware Subspace Learning

Sumin Park, Noseong Park
https://t.co/JcUfN6YT4Z [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]
💬Accepted at ICML 2026

[Artificial Intelligence Papers @SciFi]

Q-Delta: Beyond Key-Value Associative State Evolution

Sumin Park, Seojin Kim, Noseong Park
https://t.co/0iHJToLWXM [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]
💬Accepted at ICML 2026

[Artificial Intelligence Papers @SciFi]

Bridging Expert Knowledge and Automated Feature Engineering via Self-Evolution

Varun Khurana, Vijval Ekbote, Vashu Chauhan, Yaman Kumar Singla, Rajiv Ratn Shah, Balaji Krishnamurthy
https://t.co/B22oK3MG3O [𝚌𝚜.𝙰𝙸]

[Artificial Intelligence Papers @SciFi]

RAILS: Verification-Native Clearing For Agentic Commerce

Adrian de Valois-Franklin, Alex Bogdan
https://t.co/XALE4CQ2a0 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙼𝙰]

[Artificial Intelligence Papers @SciFi]

Structure-Conditioned Actor-Critic Branches for Quality-Diversity Reinforcement Learning

Lianrong Zuo, Peilan Xu, Yong Liu, Wenjian Luo
https://t.co/ue33ukzKSU [𝚌𝚜.𝙰𝙸]

[Artificial Intelligence Papers @SciFi]

Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery

Syed Rifat Raiyan, Mohsinul Kabir, Hasan Mahmud, Md Kamrul Hasan
https://t.co/sjxUxWROR6 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙻𝙶]

[Artificial Intelligence Papers @SciFi]

How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope

Jeremy Yang, Kate Zyskowski, Noah Yonack, Jerry Ma
https://t.co/CdXNhZS4Q9 [𝚌𝚜.𝙰𝙸 𝚎𝚌𝚘𝚗.𝙶𝙽]

[Artificial Intelligence Papers @SciFi]

Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle

Jiayu Wang, Weijiang Lv, Bowen Fu, Jing Fu, Jiayi Song, Lingyu Zhang, Lanxuan Xue, Luodi Chen, Zepeng Xin, Kaiyu Li, …
https://t.co/2qTYxXnSF3 [𝚌𝚜.𝙰𝙸]

[Artificial Intelligence Papers @SciFi]

Online Pandora's Box for Contextual LLM Cascading

Alexandre Belloni, Yan Chen, Yehua Wei
https://t.co/GPB2p8b4fp [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶 𝚎𝚌𝚘𝚗.𝙴𝙼 𝚜𝚝𝚊𝚝.𝙼𝙻]

[Artificial Intelligence Papers @SciFi]

Off-Policy Evaluation with Strategic Agents via Local Disclosure

Kiet Q. H. Vo, Abbavaram Gowtham Reddy, Julian Rodemann, Siu Lun Chau, Krikamol Muandet
https://t.co/Fauoxke7Kh [𝚌𝚜.𝙰𝙸]

[Artificial Intelligence Papers @SciFi]

DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

Lingyong Yan, Can Xu, Yukun Zhao, Wenxuan Li, Qingyang Chen, Jiulong Wu, Wenli Song, Xiangnan Li, Weixian Shi, Yiqun Chen, Xuchen Ma, …
https://t.co/pVR06hSchy [𝚌𝚜.𝙰𝙸]

[Artificial Intelligence Papers @SciFi]

TOPSIS-RAD: Ranking According to Desires

Leonardo Fernandes Costa, Helder Gomes Costa, Diogo Lima, Brunno Rodrigues
https://t.co/E6Gr9LXPRT [𝚌𝚜.𝙰𝙸 𝚎𝚌𝚘𝚗.𝙴𝙼]