8 papers
Tree-of-Experience: Hierarchical Experience Management for Self-Evolving Agents
Zihao Deng, Yining Zhu, Leiming Wang +6
Continual self-evolution requires LLM agents to transform environmental interactions into reliable and reusable experience. Existing methods typically refine individual trajectorie…
FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards
Zihao Deng, Yining Zhu, Leiming Wang +6
Experience-based self-evolution enables language-model agents to improve their behavior by accumulating and updating experience at test time, yet existing evaluations often assume…
Towards Safe and Robust Autonomous Vehicle Platooning: A Self-Organizing Cooperative Control Framework
Chengkai Xu, Zihao Deng, Jiaqi Liu +4
In hybrid traffic environments where human-driven vehicles (HDVs) and autonomous vehicles (AVs) coexist, achieving safe and robust decision-making for AV platooning remains a compl…
Collaborative Planning with Concurrent Synchronization for Operationally Constrained UAV-UGV Teams
Zihao Deng, Qianhuang Li, Peng Gao +4
Collaborative planning under operational constraints is an essential capability for heterogeneous robot teams tackling complex large-scale real-world tasks. Unmanned Aerial Vehicle…
NL2CA: Auto-formalizing Cognitive Decision-Making from Natural Language Using an Unsupervised CriticNL2LTL Framework
Zihao Deng, Yijia Li, Renrui Zhang +1
Cognitive computing models offer a formal and interpretable way to characterize human's deliberation and decision-making, yet their development remains labor-intensive. In this pap…
Subteaming and Adaptive Formation Control for Coordinated Multi-Robot Navigation
Zihao Deng, Peng Gao, Williard Joshua Jose +5
Coordinated multi-robot navigation is essential for robots to operate as a team in diverse environments. During navigation, robot teams usually need to maintain specific formations…