Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents
findings of EMNLP
Haoyu, Sun and Wang, Wenxuan and Mingyang, Song and Jujie, He and Weinan, Zhang and Yang, Liu and Yang, Yang and Yu, Cheng
2026
Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents
findings of EMNLP
Haoyu, Sun and Wang, Wenxuan and Mingyang, Song and Jujie, He and Weinan, Zhang and Yang, Liu and Yang, Yang and Yu, Cheng
CoEmbod: A Long-Horizon Benchmark for Multi-Agent Embodied Cooperation with Diverse Inter-Agent Dependencies
EMNLP
Xuan, Dong and Zhe, Han and Ru, Yu and Tianhao, Niu and Muzhen, Cai and xinda, lv and Qingfu, Zhu and Weinan, Zhang and Wanxiang, Che
CoEmbod: A Long-Horizon Benchmark for Multi-Agent Embodied Cooperation with Diverse Inter-Agent Dependencies
EMNLP
Xuan, Dong and Zhe, Han and Ru, Yu and Tianhao, Niu and Muzhen, Cai and xinda, lv and Qingfu, Zhu and Weinan, Zhang and Wanxiang, Che
DARTS: Diversity-Aware Reasoning Tree Search for Test-Time Scaling
findings of EMNLP
Kaifeng, Liu and Shijie, Wang and Yuanxing, Liu and Yang, Liu and Xinyi, Wang and Haozheng, Hou and Biqing, Qi and Weinan, Zhang and Ting, Liu
DARTS: Diversity-Aware Reasoning Tree Search for Test-Time Scaling
findings of EMNLP
Kaifeng, Liu and Shijie, Wang and Yuanxing, Liu and Yang, Liu and Xinyi, Wang and Haozheng, Hou and Biqing, Qi and Weinan, Zhang and Ting, Liu
SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents
findings of EMNLP
Wenxuan, Wang and Haoyu, Sun and Fukuan, Hou and Mingyang, Song and Weinan, Zhang and Yu, Cheng and Yang, Yang
SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents
findings of EMNLP
Wenxuan, Wang and Haoyu, Sun and Fukuan, Hou and Mingyang, Song and Weinan, Zhang and Yu, Cheng and Yang, Yang
Toward Detecting Modern Social Media Agents: Dataset, Experimental Analysis, and an Agent-Based Solution
findings of EMNLP
Yi, Han and Lizi, Liao and Haiqi, Lu and Yuanxing, Liu and Weinan, Zhang and Ting, Liu
Toward Detecting Modern Social Media Agents: Dataset, Experimental Analysis, and an Agent-Based Solution
findings of EMNLP
Yi, Han and Lizi, Liao and Haiqi, Lu and Yuanxing, Liu and Weinan, Zhang and Ting, Liu
Weakly Supervised Affordance Grounding via Semantic Affordance Anchoring
BMVC
Lei, Wu and Yuanxing, Liu and Ruiyu, Xiao and Xinyi, Wang and Na, Zhao and Weinan, Zhang and Ting, Liu
Weakly Supervised Affordance Grounding via Semantic Affordance Anchoring
BMVC
Lei, Wu and Yuanxing, Liu and Ruiyu, Xiao and Xinyi, Wang and Na, Zhao and Weinan, Zhang and Ting, Liu
Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations
AAAI
Yuchi, Zhang and Churui, Sun and Shiqi, Liang and Diyuan, Liu and Chao, Ji and Weinan, Zhang and Ting, Liu
Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations
AAAI
Yuchi, Zhang and Churui, Sun and Shiqi, Liang and Diyuan, Liu and Chao, Ji and Weinan, Zhang and Ting, Liu
FAER: Benchmarking VLMs for Failure-Aware Embodied Reasoning
Findings of ACL
Hao, Song and Kaifeng, Liu and Yuanxing, Liu and Xiang, Tian and Xuesong, Wang and Yifan, Chen and Weinan, Zhang and Ting, Liu
FAER: Benchmarking VLMs for Failure-Aware Embodied Reasoning
Findings of ACL
Hao, Song and Kaifeng, Liu and Yuanxing, Liu and Xiang, Tian and Xuesong, Wang and Yifan, Chen and Weinan, Zhang and Ting, Liu
PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis
CVPR
Chunji, lv and Zequn, Chen and Donglin, Di and Weinan, Zhang and Hao, Li and Chen, Wei and Yinjie, Lei and Changsheng, Li
PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis
CVPR
Chunji, lv and Zequn, Chen and Donglin, Di and Weinan, Zhang and Hao, Li and Chen, Wei and Yinjie, Lei and Changsheng, Li
When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models
ACL
Xuan, Dong and Zhe, Han and Tianhao, Niu and Qingfu, Zhu and Wanxiang, Che
When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models
ACL
Xuan, Dong and Zhe, Han and Tianhao, Niu and Qingfu, Zhu and Wanxiang, Che
Beyond Imitation: Reinforcement Learning-BasedSim-Real Co-Training for VLA Models
ICRA
Liangzhi, Shi and Shuaihang, Chen and Feng, Gao and Yinuo, Chen and Kang, Chen and Tonghe, Zhang and Hongzhi, Zang and Weinan, Zhang and Chao, Yu and Yu, Wang
Beyond Imitation: Reinforcement Learning-BasedSim-Real Co-Training for VLA Models
ICRA
Liangzhi, Shi and Shuaihang, Chen and Feng, Gao and Yinuo, Chen and Kang, Chen and Tonghe, Zhang and Hongzhi, Zang and Weinan, Zhang and Chao, Yu and Yu, Wang
BODIO: A Bit-Oriented Distance-Iterated Optimizer for Key Search with Bitwise Linear Leakage
Applied Soft Computing
Ting, Gao and Xuyang, Chen and Yuanxing, Liu and An, Wang
BODIO: A Bit-Oriented Distance-Iterated Optimizer for Key Search with Bitwise Linear Leakage
Applied Soft Computing
Ting, Gao and Xuyang, Chen and Yuanxing, Liu and An, Wang
Exploring and Distilling Multi-Dimensional Clues for Interpretable Social Bot Detection
ACL
Yi, Han and Haiqi, Lu and Lizi, Liao and Shuhan, Zhou and Yuanxing, Liu and Weinan, Zhang and Ting Liu
Exploring and Distilling Multi-Dimensional Clues for Interpretable Social Bot Detection
ACL
Yi, Han and Haiqi, Lu and Lizi, Liao and Shuhan, Zhou and Yuanxing, Liu and Weinan, Zhang and Ting Liu
Gradients with respect to semantics preserving embeddings tell the uncertainty of large language models
ICML
Mingda, Li and Rundong, Lv and Xinyu, Li and Weinan, Zhang and Ting, Liu
Gradients with respect to semantics preserving embeddings tell the uncertainty of large language models
ICML
Mingda, Li and Rundong, Lv and Xinyu, Li and Weinan, Zhang and Ting, Liu
MRPO: Magnitude-Regularized Policy Optimization via L1 Constraints
ICML
Wei, Han and Yuanxing, Liu and Mingda, Li and Ruiyu, Xiao and Weinan, Zhang and Ting, Liu
MRPO: Magnitude-Regularized Policy Optimization via L1 Constraints
ICML
Wei, Han and Yuanxing, Liu and Mingda, Li and Ruiyu, Xiao and Weinan, Zhang and Ting, Liu
RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models
RSS
Hongzhi, Zang and Mingjie, Wei and Si, Xu and Yongji, Wu and Zhen, Guo and Yuanqing, Wang and Hao, Lin and Peihong, Wang and Liangzhi, Shi and Yuqing, Xie and Zhexuan, Xu and Zhihao, Liu and Kang, Chen and Wenhao, Tang and Quanlu, Zhang and Weinan, Zhang and Chao, Yu and Yu, Wang
RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models
RSS
Hongzhi, Zang and Mingjie, Wei and Si, Xu and Yongji, Wu and Zhen, Guo and Yuanqing, Wang and Hao, Lin and Peihong, Wang and Liangzhi, Shi and Yuqing, Xie and Zhexuan, Xu and Zhihao, Liu and Kang, Chen and Wenhao, Tang and Quanlu, Zhang and Weinan, Zhang and Chao, Yu and Yu, Wang