Self-Improving Language Models for Evolutionary Program ...
Jul 10, 2025 · Many program synthesis tasks prove too challenging for even state-of-the-art language models to solve in single attempts. Search-based evolutionary methods offer a promising alternative …
Towards Neural Synthesis for SMT-Assisted Proof-Oriented ...
Sep 10, 2025 · Seeking to spur research on using AI to automate the construction of proof-oriented programs, we curate a dataset of 600K lines of open-source F⋆ programs and proofs, including …
Abstract Many program synthesis tasks prove too challeng-ing for even state-of-the-art language models to solve in single attempts. Search-based evolution-ary methods offer a promising alternative by ex …
Program Synthesis via Test-Time Transduction - AI Research ...
Sep 22, 2025 · AI-powered analysis of 'Program Synthesis via Test-Time Transduction'. We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly …
Accepted Findings Papers - ACL 2025
Accepted Findings Papers Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection Yachao Zhao, Bo Wang, Yan Wang, Dongming Zhao, Ruifang He, Yuexian …
[2511.13274] KForge: Program Synthesis for Diverse AI ...
Nov 17, 2025 · We make three key contributions: (1) introducing an iterative refinement system where the generation agent and performance analysis agent collaborate through functional and optimization …
Synergistic Utilization of LLMs for Program Synthesis
Aug 1, 2024 · Advances in Large Language Models (LLMs) have led them to be used as black boxes in several evolutionary algorithms for program synthesis. While these methods tend to be agnostic …