2026-08-12 –, Room 2
Wouldn’t it be great if Julia could program itself?
You simply tell it what you want, Julia magic happens, and you get correct-by-construction code.
In this talk, we introduce Herb.jl, a unifying program synthesis library written in Julia, that gets us closer to this goal.
While we are not fully there yet, we have significantly progressed since our last talk at JuliaCon 2024.
Herb.jl is a toolbox and framework for program synthesis: Automatically generating (not just) programs from specifications.
Since our last talk at JuliaCon 2024, Herb.jl has grown substantially, combining both reasoning about programs and LLM-guided code generation.
First, we introduce new constraint-solving techniques to Herb.jl and program synthesis:
Constraints allow us to prune large regions of possible programs, e.g., by removing symmetries and useless programs, leading to significantly faster solving times.
Second, we introduce provable LLM guidance:
In Herb.jl, large language models (LLMs) can propose candidates or search heuristics, while Herb.jl retains formal guarantees and reasoning capabilities.
In this talk, we give a brief overview of our architecture, which unifies these ideas into a single extendable pipeline.
We demonstrate how Julia’s metaprogramming and composability enable implementing new and old synthesizer ideas, and show how Herb.jl helps to synthesize not just programs.
I am a PhD student for Computer Science within the PONY lab with Sebastijan Dumancic and Neil Yorke-Smith, researching in the field of program synthesis, neuro-symbolic proving and reasoning, and their application to bioinformatics.
Check out my website for more information.
I am a PhD candidate at TU Delft, where I focus on program synthesis and applying it to scientific discovery. Currently, I am focusing on methods for synthesizing dynamical systems, with applications in biology. Alongside my own research, I work on Herb.jl, a program synthesis framework developed here at TU Delft (see: https://herb-ai.github.io/).