Research map / Large language models / Agents, code and math
Grammar Filtering for Syntax-Guided Synthesis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Filter the grammar using both predicted criticality and predicted time savings | CVC4 · PBE Strings 2019 | total synthesis time: 1304.87 seconds to 683.09 seconds; 47.65% | Helped |
| Filter the grammar using both predicted criticality and predicted time savings | CVC4 · PBE Strings 2019 | solved benchmarks | Helped |
| Use criticality prediction only, without time-savings prediction (ablation) | GRT+CVC4 · PBE Strings 2019 | running time | Hurt |
| Use criticality prediction only, without time-savings prediction (ablation) | GRT+CVC4 · PBE Strings 2019, benchmarks that did not timeout on CVC4 | benchmarks with increased running time: 53 out of the 62 benchmarks | Hurt |
| Filter the grammar using both predicted criticality and predicted time savings | CVC4 · PBE Strings 2019 | synthesized program size: 806 to 789 | Helped |
| Use the reduced grammar without falling back to the full grammar | GRT+CVC4 · PBE Strings 2019 | synthesis time | No clear effect |
Closest papers by meaning
- Is Programming by Example Solved by LLMs? (NeurIPS 2024 · similarity 0.88)
- Reinforcement Learning and Data-Generation for Syntax-Guided Synthesis (AAAI 2024 · similarity 0.87)
- Generating Pragmatic Examples to Train Neural Program Synthesizers (ICLR 2024 · similarity 0.83)
- Online Prompt Selection for Program Synthesis (AAAI 2025 · similarity 0.83)
- Learning to Reason via Program Generation, Emulation, and Search (NeurIPS 2024 · similarity 0.83)
- HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis (NeurIPS 2024 · similarity 0.82)
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.