paper-with-me

Papers

AlgoPilot: Fully Autonomous Program Synthesis Without Human-Written Programs

2025-01-11 · Xiaoxin Yin

Program synthesis has traditionally relied on human-provided specifications, examples, or prior knowledge to generate functional algorithms. Existing methods either emulate human-written algorithms or solve specific tasks without generating reusable programmatic logic, limiting their ability to create novel algorithms. We introduce AlgoPilot, a groundbreaking approach for fully automated program synthesis without human-written programs or trajectories. AlgoPilot leverages reinforcement learning (RL) guided by a Trajectory Language Model (TLM) to synthesize algorithms from scratch. The TLM, trained on trajectories generated by random Python functions, serves as a soft constraint during the RL process, aligning generated sequences with patterns likely to represent valid algorithms. Using sorting as a test case, AlgoPilot demonstrates its ability to generate trajectories that are interpretable as classical algorithms, such as Bubble Sort, while operating without prior algorithmic knowledge. This work establishes a new paradigm for algorithm discovery and lays the groundwork for future advancements in autonomous program synthesis.

📄 PDF Abstract BibTeX arXiv:2501.06423

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingProgram SynthesisReinforcement Learning (RL)valid

Similar Papers 제목 키워드 기반

Fully Autonomous Programming with Large Language Models

2023-04-20 · Vadim Liventsev, Anastasiia Grishina, Aki Härmä, Leon Moonen

Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome": they tend to generate programs that semantically resemble the correct answer (as measured by text similarity metri…

Program RepairProgram Synthesistext similarity

Large Language Models Synergize with Automated Machine Learning

2024-05-06 · Jinglue Xu, Jialong Li, Zhen Liu, Nagar Anthel Venkatesh Suryanarayanan 외

Recently, program synthesis driven by large language models (LLMs) has become increasingly popular. However, program synthesis for machine learning (ML) tasks still poses significant challenges. This paper explores a nov…

AutoMLCode GenerationProgram Synthesis

Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models

2025-03-10 · Anastasiia Grishina, Vadim Liventsev, Aki Härmä, Leon Moonen

Program synthesis with Large Language Models (LLMs) suffers from a "near-miss syndrome": the generated code closely resembles a correct solution but fails unit tests due to minor errors. We address this with a multi-agen…

HumanEvalProgram Synthesis

Semi-supervised Learning From Demonstration Through Program Synthesis: An Inspection Robot Case Study

2020-07-23 · Simón C. Smith, Subramanian Ramamoorthy

Semi-supervised learning improves the performance of supervised machine learning by leveraging methods from unsupervised learning to extract information not explicitly available in the labels. Through the design of a sys…

ClusteringcounterfactualDecision MakingModel Predictive Control+1

Program-Synthesis-Driven Autodesign of Universal Unitary Operators

2026-07-11 · Yifei Zhang, Dong Chen, Fan Wang, Wenrui Zhang 외 arxiv

We demonstrate that AI-driven program synthesis can autonomously discover fundamental strategies for decomposing unitary matrices in photonic networks. By extending DreamCoder to complex-valued linear algebra, the system…

Program Synthesis