Programming with a read-eval-synth loop
Hila Peleg, Roi Gabay, Shachar Itzhaky, Eran Yahav
Abstract
A frequent programming pattern for small tasks, especially expressions, is to repeatedly evaluate the program on an input as its editing progresses. The Read-Eval-Print Loop (REPL) interaction model has been a successful model for this programming pattern. We present the new notion of Read-Eval-Synth Loop (RESL) that extends REPL by providing in-place synthesis on parts of the expression marked by the user. RESL eases programming by synthesizing parts of a required solution. The underlying synthesizer relies on a partial solution from the programmer and a few examples. RESL hinges on bottom-up synthesis with general predicates and sketching, generalizing programming by example. To make RESL practical, we present a formal framework that extends observational equivalence to non-example specifications. We evaluate RESL by conducting a controlled within-subjects user-study on 19 programmers from 8 companies, where programmers are asked to solve a small but challenging set of competitive programming problems. We find that programmers using RESL solve these problems with far less need to edit the code themselves and by browsing documentation far less. In addition, they are less likely to leave a task unfinished and more likely to be correct.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get 1265c463-18f2-4b46-865e-80a369e8f96dCited by top-tier papers7
- Grounded Copilot: How Programmers Interact with Code-Generating ModelsShraddha Barke, Michael B. James, Nadia PolikarpovaOOPSLA 2023 · 408 citations
- Validating AI-Generated Code with Live ProgrammingKasra Ferdowsi, Ruanqianqian (Lisa) Huang, Michael B. James, Nadia Polikarpova et al.CHI 2024 · 27 citations
- Representing Partial Programs with Blended Abstract SemanticsMaxwell I. Nye, Yewen Pu, Matthew Bowers, Jacob Andreas et al.ICLR 2021 · 23 citations
- LooPy: interactive program synthesis with control structuresKasra Ferdowsifard, Shraddha Barke, Hila Peleg, Sorin Lerner et al.OOPSLA 2021 · 18 citations
- Synthesizing analytical SQL queries from computation demonstrationXiangyu Zhou, Rastislav Bodík, Alvin Cheung, Chenglong WangPLDI 2022 · 11 citations
Related papers
- Interactive Program Synthesis by Augmented ExamplesTianyi Zhang, London Lowmanstone, Xinyu Wang, Elena L. GlassmanUIST 2020 · 57 citations
- Small-Step Live Programming by ExampleKasra Ferdowsifard, Allen Ordookhanians, Hila Peleg, Sorin Lerner et al.UIST 2020 · 40 citations
- Generating Pragmatic Examples to Train Neural Program SynthesizersSaujas Vaduguru, Daniel Fried, Yewen PuICLR 2024 · 7 citations
- SynGuar: guaranteeing generalization in programming by exampleBo Wang, Teodora Baluta, Aashish Kolluri, Prateek SaxenaFSE 2021
- Exploring the Learnability of Program Synthesizers by Novice ProgrammersDhanya Jayagopal, Justin Lubin, Sarah E. ChasinsUIST 2022 · 40 citations
