Tag
This paper proposes Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment (LCA), a framework that jointly learns credit assignment and reward modeling under a weakest-link principle, formulated as a Multiple Instance Learning problem with Softmax-Weighted-Sum pooling. Experiments show it outperforms existing outcome-supervised PRMs across multiple tasks.
StepPRM-RTL is a novel framework combining stepwise trajectory modeling, process-reward modeling (PRM), and retrieval-augmented fine-tuning (RAFT) to improve LLM-based RTL code generation for Verilog and VHDL, outperforming prior methods by over 10% in functional correctness metrics.