Assuage: Assembly Synthesis Using A Guided Exploration
Authors
Assembly programming is challenging, even for experts. Program synthesis, as an alternative to manual implementation, has the potential to enable both expert and non-expert users to generate programs in an automated fashion. However, current tools and techniques are unable to synthesize assembly programs larger than a few instructions. We present Assuage: ASsembly Synthesis Using A Guided Exploration, which is a parallel interactive assembly synthesizer that engages the user as an active collaborator, enabling synthesis to scale beyond current limits. Using Assuage, users can provide two types of semantically meaningful hints that expedite synthesis and allow for exploration of multiple possibilities simultaneously. Assuage exposes information about the underlying synthesis process using multiple representations to help users guide synthesis. We conducted a within-subjects study with twenty-one participants working on assembly programming tasks. With Assuage, participants with a wide range of expertise were able to achieve significantly higher success rates, perceived less subjective workload, and preferred the usefulness and usability of Assuage over a state of the art synthesis tool.
Research Questions / Practical Problems
Question signals indexed for this paper.
- 80%
Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chat
CHI '24· Human-LLM Collaboration +1
- 80%
Trade-offs in Sampling and Search for Early-stage Interactive Machine Learning
IUI '22· Human-LLM Collaboration +1
- 80%
Hypothesizer: A Hypothesis-Based Debugger to Find and Test Debugging Hypotheses
UIST '23· Immersion & Presence Research +2
- 75%
Computational Interaction: Theory and Practice
CHI '18· Computational Methods in HCI
- 75%
Model-based Evaluation of Recall-based Interaction Techniques
CHI '24· Computational Methods in HCI
- 75%
MAPLE: Mobile App Prediction Leveraging Large Language Model Embeddings
UbiComp '24· Human-LLM Collaboration
- 75%
Small-Step Live Programming by Example
UIST '20· Computational Methods in HCI
- 75%
LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation
UIST '24· Human-LLM Collaboration
- 67%
Crystalline: Lowering the Cost for Developers to Collect and Organize Information for Decision Making
CHI '22· Human-LLM Collaboration +2
- 60%
Visualizing API Usage Examples at Scale
CHI '18· Interactive Data Visualization +1
Based on Jaccard similarity of research subtopics & professions (≥60%)