Reinforcement Learning with Shaped Rewards vs. Policy Gradients on DS-1000 Code Generation

This report synthesises findings from 11 peer-reviewed papers addressing the following research question: How does the pass@k accuracy of reinforcement learning with shaped rewards compare to standard policy gradients when evaluating LLMs on the DS-1000 code generation benchmark. Large Language Models (LLMs) have garnered remarkable advancements across diverse code-related tasks, known as Code LLMs, particularly in code generation that generates source code with LLM from natural language descriptions. This burgeoning field has captured significant. 11 claims were extracted from source literature; 10 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the pass@k accuracy of reinforcement learning with shaped rewards compare to standard policy gradients when evaluating LLMs on the DS-1000 code generation benchmark?

Autonomous literature synthesis. Automated review score: 8.5/10. Full text and citation available at Assignee Research.