AlgoPilot: Fully Autonomous Program Synthesis Without Human-Written Programs
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingProgram SynthesisReinforcement Learning (RL)validSimilar Papers 제목 키워드 기반
Fully Autonomous Programming with Large Language Models
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 similarityLarge Language Models Synergize with Automated Machine Learning
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 SynthesisFully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models
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 SynthesisSemi-supervised Learning From Demonstration Through Program Synthesis: An Inspection Robot Case Study
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+1Program-Synthesis-Driven Autodesign of Universal Unitary Operators
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