# Exploring Dynamic Selection of Branch Expansion Orders for Code Generation

arXiv: https://arxiv.org/abs/2106.00261 · HTML: https://mlsanity.com/paper/2106.00261/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 1 Jun 2021.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Levenshtein Transformer](https://mlsanity.com/paper/1905.11006/) (2019)
- [Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow](https://mlsanity.com/paper/1805.08949/) (2018)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [Insertion Transformer: Flexible Sequence Generation via Insertion Operations](https://mlsanity.com/paper/1902.03249/) (2019)
- [Coarse-to-Fine Decoding for Neural Semantic Parsing](https://mlsanity.com/paper/1805.04793/) (2018)
- [Abstract Syntax Networks for Code Generation and Semantic Parsing](https://mlsanity.com/paper/1704.07535/) (2017)
- [TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation](https://mlsanity.com/paper/1810.02720/) (2018)
- [Latent Predictor Networks for Code Generation](https://mlsanity.com/paper/1603.06744/) (2016)
- [Code Generation as a Dual Task of Code Summarization](https://mlsanity.com/paper/1910.05923/) (2019)
- [TreeGen: A Tree-Based Transformer Architecture for Code Generation](https://mlsanity.com/paper/1911.09983/) (2019)
- [Non-Monotonic Sequential Text Generation](https://mlsanity.com/paper/1902.02192/) (2019)
- [Insertion-based Decoding with automatically Inferred Generation Order](https://mlsanity.com/paper/1902.01370/) (2019)
- [Retrieval-Based Neural Code Generation](https://mlsanity.com/paper/1808.10025/) (2018)
- [Incorporating External Knowledge through Pre-training for Natural Language to Code Generation](https://mlsanity.com/paper/2004.09015/) (2020)
- [Program Synthesis and Semantic Parsing with Learned Code Idioms](https://mlsanity.com/paper/1906.10816/) (2019)
- [A Grammar-Based Structural CNN Decoder for Code Generation](https://mlsanity.com/paper/1811.06837/) (2018)
- [Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning](https://mlsanity.com/paper/2010.04314/) (2020)
- [Asynchronous Bidirectional Decoding for Neural Machine Translation](https://mlsanity.com/paper/1801.05122/) (2018)
- [Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning](https://mlsanity.com/paper/2105.14796/) (2021)

## Built on by (most cited first, 10 of 10)

- [Large Language Model-Aware In-Context Learning for Code Generation](https://mlsanity.com/paper/2310.09748/) (2023)
- [StructCoder: Structure-Aware Transformer for Code Generation](https://mlsanity.com/paper/2206.05239/) (2022)
- [EpiCoder: Encompassing Diversity and Complexity in Code Generation](https://mlsanity.com/paper/2501.04694/) (2025)
- [Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models](https://mlsanity.com/paper/2407.00456/) (2024)
- [Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation](https://mlsanity.com/paper/2106.06125/) (2021)
- [Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generation](https://mlsanity.com/paper/2208.10091/) (2022)
- [CodePAD: Sequence-based Code Generation with Pushdown Automaton](https://mlsanity.com/paper/2211.00818/) (2022)
- [Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production](https://mlsanity.com/paper/2302.09300/) (2023)
- [UniGenCoder: Merging Seq2Seq and Seq2Tree Paradigms for Unified Code Generation](https://mlsanity.com/paper/2502.12490/) (2025)
- [Antecedent Predictions Are More Important Than You Think: An Effective Method for Tree-Based Code Generation](https://mlsanity.com/paper/2208.09998/) (2022)

## Abstract (arXiv)

Due to the great potential in facilitating software development, code generation has attracted increasing attention recently. Generally, dominant models are Seq2Tree models, which convert the input natural language description into a sequence of tree-construction actions corresponding to the pre-order traversal of an Abstract Syntax Tree (AST). However, such a traversal order may not be suitable for handling all multi-branch nodes. In this paper, we propose to equip the Seq2Tree model with a context-based Branch Selector, which is able to dynamically determine optimal expansion orders of branches for multi-branch nodes. Particularly, since the selection of expansion orders is a non-differentiable multi-step operation, we optimize the selector through reinforcement learning, and formulate the reward function as the difference of model losses obtained through different expansion orders. Experimental results and in-depth analysis on several commonly-used datasets demonstrate the effectiveness and generality of our approach. We have released our code at https://github.com/DeepLearnXMU/CG-RL.