Research map / Large language models / Agents, code and math
Program Synthesis with Pragmatic Communication
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 |
|---|---|---|---|
| Use the pragmatic listener L1 instead of the literal listener L0 | Human communication with the grid-pattern synthesizer · Grid-pattern program synthesis | mean number of symbols used: mean difference of 2.8 moves | Helped |
| Use pragmatic listener L1 instead of crafted-prior listener Lp | S1 speaker · Grid-pattern program synthesis | mean number of utterances required: 3.8 -> 3.34 | Helped |
| Use human examples with pragmatic listener L1 rather than literal listener L0 | Human speaker · Grid-pattern program synthesis | mean number of symbols required for successful communication | No clear effect |
Closest papers by meaning
- Generating Pragmatic Examples to Train Neural Program Synthesizers (ICLR 2024 · similarity 0.89)
- Learning to Reason via Program Generation, Emulation, and Search (NeurIPS 2024 · similarity 0.86)
- Program Synthesis via Test-Time Transduction (NeurIPS 2025 · similarity 0.86)
- Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation (ICML 2025 · similarity 0.85)
- Once Upon an Input: Reasoning via Per-Instance Program Synthesis (NeurIPS 2025 · similarity 0.85)
- From I/O to Code with Discovery Agent (NeurIPS 2026 · similarity 0.84)
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.