Research map / Large language models / Agents, code and math
Dynamic-Static Synergistic Selection Method for Candidate Code Solutions with Generated Test Cases
Ren-Biao Liu, Jiang-Tian Xue, Chao-Zeng Ma, Hui Sun, Xin-Ye Li, Ming Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add dynamic execution-consistency scoring (ablation) | DS3 (GPT-3.5-Turbo) · HumanEval | Pass@1: 68.29 -> 81.71 | Improved |
| add static quality scores (Pylint and cyclomatic complexity) (ablation) | DS3 (GPT-3.5-Turbo) · HumanEval | Pass@1: 79.88 -> 81.71 | Improved |
| add score integration ranking (ablation) | DS3 (GPT-3.5-Turbo) · HumanEval | Pass@1: 70.99 -> 81.71 | Improved |
| add selection at all (DS3 vs no selection) (ablation) | DS3 (GPT-3.5-Turbo) · HumanEval | Pass@5: 83.15 -> 82.93 | No clear effect |
| DS3 selection vs CODET | DS3 (GPT-3.5-Turbo) · HumanEval+ | Pass@1: 67.87 -> 73.17 | Improved |
| DS3 selection vs CODET | DS3 (GPT-3.5-Turbo) · MBPP | Pass@1: 71.90 -> 76.11 | Improved |
| DS3 on top of GPT-3.5-Turbo vs GPT-4 | DS3 (GPT-3.5-Turbo) · HumanEval | Pass@1: 81.48 -> 81.71 | Improved |
| DS3 vs B4 on CodeLlama generator | DS3 (GPT-3.5-Turbo) · HumanEval | Pass@1: 64.8 -> 66.2 | Improved |
| DS3 vs B4 on StarCoder generator | DS3 (GPT-3.5-Turbo) · HumanEval | Pass@1: 59.3 -> 59.3 | No clear effect |
| DS3 vs CODET at k=5 | DS3 (GPT-3.5-Turbo) · HumanEval | Pass@5: 78.30 -> 82.93 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CODET — CodeT: Code Generation with Generated Tests (ICLR 2023) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer (ICML 2026 · similarity 0.87)
- SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents (NeurIPS 2024 · similarity 0.87)
- Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation (NeurIPS 2024 · similarity 0.86)
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code (ICLR 2025 · similarity 0.86)
- DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination (ICML 2025 · similarity 0.86)
- rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
