Papers Program Synthesis
“Program Synthesis” 태그가 달린 논문 538편 · 필터 해제
Transductively Informed Inductive Program Synthesis
Abstraction and reasoning in program synthesis has seen significant progress through both inductive and transductive paradigms. Inductive approaches generate a program or latent function from input-output examples, which…
Program SynthesisPoE-World: Compositional World Modeling with Products of Programmatic Experts
Learning how the world works is central to building AI agents that can adapt to complex environments. Traditional world models based on deep learning demand vast amounts of training data, and do not flexibly update their…
Montezuma's RevengeProgram SynthesisEnhancing Code Generation via Bidirectional Comment-Level Mutual Grounding
Large Language Models (LLMs) have demonstrated unprecedented capability in code generation. However, LLM-generated code is still plagued with a wide range of functional errors, especially for complex programming tasks th…
Code GenerationComment GenerationHumanEvalProgram SynthesisRewriting Pre-Training Data Boosts LLM Performance in Math and Code
The performance of large language models (LLMs) in program synthesis and mathematical reasoning is fundamentally limited by the quality of their pre-training corpora. We introduce two openly licensed datasets, released u…
Code GenerationGSM8KHumanEvalMath+2QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach
Heterogeneous deep learning systems (DLS) such as GPUs and ASICs have been widely deployed in industrial data centers, which requires to develop multiple low-level tensor programs for different platforms. An attractive s…
Code GenerationGPUProgram SynthesisOSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification
We introduce OSVBench, a new benchmark for evaluating Large Language Models (LLMs) in generating complete specification code pertaining to operating system kernel verification tasks. The benchmark first defines the speci…
BenchmarkingCode GenerationProgram SynthesisGPU accelerated program synthesis: Enumerate semantics, not syntax!
Program synthesis is an umbrella term for generating programs and logical formulae from specifications. With the remarkable performance improvements that GPUs enable for deep learning, a natural question arose: can we al…
CPUGPUProgram SynthesisTinyverseGP: Towards a Modular Cross-domain Benchmarking Framework for Genetic Programming
Over the years, genetic programming (GP) has evolved, with many proposed variations, especially in how they represent a solution. Being essentially a program synthesis algorithm, it is capable of tackling multiple proble…
BenchmarkingProgram SynthesisSymbolic RegressionDeQompile: quantum circuit decompilation using genetic programming for explainable quantum architecture search
Demonstrating quantum advantage using conventional quantum algorithms remains challenging on current noisy gate-based quantum computers. Automated quantum circuit synthesis via quantum machine learning has emerged as a p…
Program SynthesisQuantum Machine LearningSymbolic RegressionCodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis
Inductive program synthesis, or programming by example, requires synthesizing functions from input-output examples that generalize to unseen inputs. While large language model agents have shown promise in programming tas…
BenchmarkingLarge Language ModelProgram SynthesisSynthesizing world models for bilevel planning
Modern reinforcement learning (RL) systems have demonstrated remarkable capabilities in complex environments, such as video games. However, they still fall short of achieving human-like sample efficiency and adaptability…
Large Language ModelProgram Synthesisreinforcement-learningReinforcement Learning+1Research Vision: Multi-Agent Path Planning for Cops And Robbers Via Reactive Synthesis
We propose the problem of multi-agent path planning for a generalization of the classic Cops and Robbers game via reactive synthesis. Specifically, through the application of LTLt and Coordination Synthesis, we aim to ch…
Program SynthesisTikZero: Zero-Shot Text-Guided Graphics Program Synthesis
With the rise of generative AI, synthesizing figures from text captions becomes a compelling application. However, achieving high geometric precision and editability requires representing figures as graphics programs in …
Program SynthesisShedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model
Task decomposition is a fundamental mechanism in program synthesis, enabling complex problems to be broken down into manageable subtasks. ExeDec, a state-of-the-art program synthesis framework, employs this approach by c…
Program SynthesisAn Empirical Comparison of Cost Functions in Inductive Logic Programming
Recent inductive logic programming (ILP) approaches learn optimal hypotheses. An optimal hypothesis minimises a given cost function on the training data. There are many cost functions, such as minimising training error, …
Inductive logic programmingProgram 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 SynthesisMachine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics
With recent dramatic increases in AI system capabilities, there has been growing interest in utilizing machine learning for reasoning-heavy, quantitative tasks, particularly mathematics. While there are many resources ca…
Abstract AlgebraProgram SynthesisAutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications
The advent of Large Language Models (LLMs) has profoundly transformed our lives, revolutionizing interactions with AI and lowering the barrier to AI usage. While LLMs are primarily designed for natural language interacti…
Program SynthesisFactorio Learning Environment
Large Language Models (LLMs) are rapidly saturating existing benchmarks, necessitating new open-ended evaluations. We introduce the Factorio Learning Environment (FLE), based on the game of Factorio, that tests agents in…
Program SynthesisSpatial ReasoningGPIoT: Tailoring Small Language Models for IoT Program Synthesis and Development
Code Large Language Models (LLMs) enhance software development efficiency by automatically generating code and documentation in response to user requirements. However, code LLMs cannot synthesize specialized programs whe…
Code GenerationProgram SynthesisRAGRetrieval-augmented Generation