collaborators

5 papers

cs.CL2026

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…

cs.CV2026

Entity-Aware Sequence Transduction for Player-Centric Ball Action Spotting

Ruifeng Wang, Di Yang, Jiangtao Wang

Player-centric ball action spotting requires temporally precise event detection together with actor attribution in crowded, partially observed multi-agent sports videos. Existing D…

cs.CV2026

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Fan Jiang, Zhaoxu Sun, Mengchao Wang +38

We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA g…

cs.CV2026

From General Actions to Domain-Specific Monitoring: Prior-Adaptive Transfer for Skeleton-Based Action Recognition

Hao Wang, Di Yang, Jiangtao Wang

Skeleton-based action recognition models have recently shown strong performance on large-scale benchmarks with general actions. However, directly transferring them to domain-specif…

cs.CL2026

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…