Research Agent - AI科研助理

Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels

作者: Zhuchenyang Liu, Yao Zhang, Yu Xiao 日期: 2026-07-27 GRPO

AI 总结

总结生成失败，请查看原文。

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

作者: Tianyi Men, Zhuoran Jin, Kang Liu, Jun Zhao 日期: 2026-07-27 GRPO

AI 总结

总结生成失败，请查看原文。

MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents

作者: Guofeng Zhang, Yizeng Quan, Huaiyi Fang, Jianwei Lv, Jinyao Liu, Xunxu Duan, Lening An, Yu Ouyang, Junfeng Wang 日期: 2026-07-21 LLM

AI 总结

总结生成失败，请查看原文。

Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning

作者: Heyang Jiang, Henry Liu, Baharan Mirzasoleiman 日期: 2026-07-24 LLM

AI 总结

总结生成失败，请查看原文。

Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning

作者: Guanqun Zhao, Zijun Xie, Binbin Zheng, Enlei Gong, Jiafeng Lu, Yehan Yang, Aoqi Hu, Zeyu Chen 日期: 2026-07-24 LLM

AI 总结

总结生成失败，请查看原文。

Training Language Models to Cooperate with Inference-Time Controllers

作者: Moumita Choudhury, Vanshaj Khattar, Jing Liu, Toshiaki Koike-Akino, Ankush Chakrabarty, Shlomo Zilberstein, Ye Wang 日期: 2026-07-26 LLM

AI 总结

总结生成失败，请查看原文。

RESTOR: Automated Test Oracle Generation for RESTful APIs via Reinforcement Learning

作者: Xun Zhou, Zhen Dong, Mingyu Ren, Qiang Li, JunJie Li, Sifan Wang, Xiaolong Yu, Chaofeng Sha, Xin Peng 日期: 2026-07-27 LLM

AI 总结

总结生成失败，请查看原文。

Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding

作者: Yueru Luo, Xu Yan, Changqing Zhou, Yiming Yang, Chao Zhan, Shuqi Mei, Chao Zheng, Zhen Li 日期: 2026-07-27 LLM

AI 总结

总结生成失败，请查看原文。

CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models

作者: Mingxuan Sun 日期: 2026-07-27 LLM

AI 总结

总结生成失败，请查看原文。

Simulating Tenant Responses to Energy Policy Interventions with Transaction-Cost-Aware LLM Age

作者: Weijie Xia, Stefanie Horian, Hanyue Huang, Queena K. Qian, Jie Yang, Pedro P. Vergara Barrios 日期: 2026-07-27 LLM

AI 总结

总结生成失败，请查看原文。

PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution

作者: Yang Liu, Weixing Chen, Xinshuai Song, Tao Pu, Siwen Mo, Yongjie Bai, Zihao Chen, Qianran Sun, Liruo Zhong, Ying Shen, Liang Lin 日期: 2026-07-18 world action models

AI 总结

总结生成失败，请查看原文。

Patch Policy: Efficient Embodied Control via Dense Visual Representations

作者: Gaoyue Zhou, Zichen Jeff Cui, Ada Langford, Bowen Tan, Yann LeCun, Lerrel Pinto 日期: 2026-07-20 world model

AI 总结

总结生成失败，请查看原文。

Masked Visual Actions for Unified World Modeling

作者: Hadi Alzayer, Wenlong Huang, Haonan Chen, Christopher Luey, Lvmin Zhang, Maneesh Agrawala, Gordon Wetzstein, Li Fei-Fei, Yilun Du, Jiajun Wu, Jia-Bin Huang 日期: 2026-07-21 world model

AI 总结

总结生成失败，请查看原文。

Addressing the Orchestration Gap in Generalist Robots via Physical Agency

作者: Liane Galanti, Dhruv Shah, Tri Dao 日期: 2026-07-23 world action models

AI 总结

总结生成失败，请查看原文。

Toward Goal-Agnostic Joint-Embedding Predictive Control of Partial Differential Equations

作者: Jonathan Gallagher, Roberto Guglielmi 日期: 2026-07-21 world model

AI 总结

总结生成失败，请查看原文。

Persistent Computational State: A Session-Centric Runtime for Generative World Models

作者: Zhen Lin 日期: 2026-07-23 world model