Preprint
Sep 2026
TIPCODER: Reinforcement Learning Boosted Test-time Instruction Proposer for Code Generation
Test-time scaling for code generation typically explores the solution space by sampling multiple programs from a fixed instruction. We study a complementary direction: instance-level instruction-space exploration. Our observation is that many coding failures stem from missing constraints, overlooked edge cases, or misl...
Minyu Chen, Si-Hao Wu, Ling-I Wu et al.
· 0 citations