mlsanityData to 14 Oct 2026

Can You Improve My Code? Optimizing Programs with Local Search

arXiv 2307.05603 ↗First posted 10 Jul 2023cs.SE cs.LG cs.PLcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper introduces a local search method for improving an existing program with respect to a measurable objective. Program Optimization with Locally Improving Search (POLIS) exploits the structure of a program, defined by its lines. POLIS improves a single line of the program while keeping the remaining lines fixed, using existing brute-force synthesis algorithms, and continues iterating until it is unable to improve the program's performance. POLIS was evaluated with a 27-person user study, where participants wrote programs attempting to maximize the score of two single-agent games: Lunar Lander and Highway. POLIS was able to substantially improve the participants' programs with respect to the game scores. A proof-of-concept demonstration on existing Stack Overflow code measures applicability in real-world problems. These results suggest that POLIS could be used as a helpful programming assistant for programming problems with measurable objectives.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 13 of its 44 references that are in the map. First posted on arXiv 10 Jul 2023.

Builds on

13 of 44 references.

References · 13

  1. 2018Programmatically Interpretable Reinforcement Learningcited by 193
  2. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  3. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 161
  4. 2016DeepCoder: Learning to Write Programscited by 149
  5. 2017RobustFill: Neural Program Learning under Noisy I/Ocited by 126
  6. 2018Neural-Guided Deductive Search for Real-Time Program Synthesis from Examplescited by 39
  7. 2021A Survey on Machine Learning Techniques for Source Code Analysiscited by 24
  8. 2021Learning to Complete Code with Sketchescited by 23
  9. 2020Just-in-Time Learning for Bottom-Up Enumerative Synthesiscited by 18
  10. 2019Synthetic Datasets for Neural Program Synthesiscited by 15
  11. 2022What can we Learn Even From the Weakest? Learning Sketches for Programmatic Strategiescited by 11
  12. 2020The Effectiveness of Supervised Machine Learning Algorithms in Predicting Software Refactoringcited by 9
1 more
  1. 2021Improving Reinforcement Learning with Human Assistance: An Argument for Human Subject Studies with HIPPO Gymcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Learning Game-Playing Agents with Generative Code Optimizationcited by 8