Scholar
Lu Pan
Google Scholar ID: yTOVq-kAAAAJ
tencent
知识图谱、事件图谱、神经网路、文本生成
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
372
H-index
4
i10-index
4
Publications
9
Co-authors
0
Contact
No contact links provided.
Publications
11 items
How Much, Then Where: Credit-Conserving Action-to-Token Allocation for Multi-Turn Agent Reinforcement Learning
2026
Cited
0
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
2026
Cited
0
Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation
2026
Cited
0
ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments
2026
Cited
0
Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
2026
Cited
0
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
2026
Cited
0
Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning
2026
Cited
0
From $\boldsymbol{\logπ}$ to $\boldsymbolπ$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
2026
Cited
0
Load more
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
