7 papers
PATH-Bench: Path-Dependent Evaluation of Lifelong Agents
Xidong Yang, Xingyi Zhang, Wenhao Li +7
Lifelong LLM agents increasingly adapt through external learning states that store past interactions as retrievable memories or reusable skills, yet existing benchmarks rarely acco…
Agentic Episodic Control
Xidong Yang, Wenhao Li, Junjie Sheng +4
Reinforcement learning (RL) remains fundamentally limited by poor data efficiency and weak generalization. Prior episodic RL methods attempt to alleviate this via external memory m…
AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization
Jiehao Wu, Zixiao Huang, Wenhao Li +3
Optimizing AscendC (Ascend C) operators for Ascend NPUs is difficult for two reasons. First, unlike CUDA, the ecosystem offers few public kernels to learn from. Second, performance…
HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning
Beibei Xu, Yutong Ye, Chuyun Shen +3
Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on…
TextAtari: 100K Frames Game Playing with Language Agents
Wenhao Li, Wenwu Li, Chuyun Shen +8
We present TextAtari, a benchmark for evaluating language agents on very long-horizon decision-making tasks spanning up to 100,000 steps. By translating the visual state representa…
Interactive 3D Medical Image Segmentation with SAM 2
Chuyun Shen, Wenhao Li, Yuhang Shi +1
Interactive medical image segmentation (IMIS) has shown significant potential in enhancing segmentation accuracy by integrating iterative feedback from medical professionals. Howev…