Can Lv

Identifiers

• name variant Can Lv 0.60 · backfill

Papers (2)

1. Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning cs.LG · 2026 · author #1
2. HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems cs.CL · 2026 · author #2

Mentions

• 2606.03361 #1 · arxiv_oai · confidence 0.70 Can Lv
• 2606.01779 #2 · arxiv_oai · confidence 0.70 Can Lv

Frequent Coauthors

• Heng Chang 2 shared papers
• Mingju Chen 2 shared papers
• Shiji Zhou 2 shared papers
• Guibin Zhang 1 shared papers