Papers Program Synthesis
“Program Synthesis” 태그가 달린 논문 538편 · 필터 해제
Program Synthesis Dialog Agents for Interactive Decision-Making
Many real-world eligibility problems, ranging from medical diagnosis to tax planning, can be mapped to decision problems expressed in natural language, wherein a model must make a binary choice based on user features. La…
Code GenerationDecision MakingMedical DiagnosisProgram SynthesisVisual Agentic AI for Spatial Reasoning with a Dynamic API
Visual reasoning -- the ability to interpret the visual world -- is crucial for embodied agents that operate within three-dimensional scenes. Progress in AI has led to vision and language models capable of answering ques…
Program SynthesisSpatial ReasoningVisual ReasoningProving the Coding Interview: A Benchmark for Formally Verified Code Generation
We introduce the Formally Verified Automated Programming Progress Standards, or FVAPPS, a benchmark of 4715 samples for writing programs and proving their correctness, the largest formal verification benchmark, including…
Automated Theorem ProvingCode GenerationProgram SynthesisCODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging
Large Language Models (LLMs) have made significant strides in code generation and problem solving. Current approaches employ external tool-based iterative debuggers that use compiler or other tool-based runtime feedback …
Code GenerationHumanEvalmbppProgram SynthesisLearning Semantics-aware Search Operators for Genetic Programming
Fitness landscapes in test-based program synthesis are known to be extremely rugged, with even minimal modifications of programs often leading to fundamental changes in their behavior and, consequently, fitness values. R…
Graph Neural NetworkProgram SynthesisSymbolic RegressionQualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks
We introduce QualityFlow, a dynamic agentic workflow for program synthesis. Given the English description of a programming problem and a set of unit tests, the model's goal is to synthesize the correct program that solve…
Code GenerationHumanEvalLanguage ModelingLanguage Modelling+3AlgoPilot: 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 task…
Language ModelingLanguage ModellingProgram SynthesisReinforcement Learning (RL)+1Online Prompt Selection for Program Synthesis
Large Language Models (LLMs) demonstrate impressive capabilities in the domain of program synthesis. This level of performance is not, however, universal across all tasks, all LLMs and all prompting styles. There are man…
Program SynthesisMMFactory: A Universal Solution Search Engine for Vision-Language Tasks
With advances in foundational and vision-language models, and effective fine-tuning techniques, a large number of both general and special-purpose models have been developed for a variety of visual tasks. Despite the fle…
Program SynthesisEcoSearch: A Constant-Delay Best-First Search Algorithm for Program Synthesis
Many approaches to program synthesis perform a combinatorial search within a large space of programs to find one that satisfies a given specification. To tame the search space blowup, previous works introduced probabilis…
Program SynthesisDesign2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments. However, existing uni-modal sewing pattern generation models struggle t…
Program SynthesisConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)
The Abstraction and Reasoning Corpus (ARC) poses a significant challenge to artificial intelligence, demanding broad generalization and few-shot learning capabilities that remain elusive for current deep learning methods…
ARCFew-Shot LearningProgram SynthesisFrom Code to Play: Benchmarking Program Search for Games Using Large Language Models
Large language models (LLMs) have shown impressive capabilities in generating program code, opening exciting opportunities for applying program synthesis to games. In this work, we explore the potential of LLMs to direct…
Atari GamesBenchmarkingProgram SynthesisTAGARC Prize 2024: Technical Report
As of December 2024, the ARC-AGI benchmark is five years old and remains unbeaten. We believe it is currently the most important unsolved AI benchmark in the world because it seeks to measure generalization on novel task…
ARCProgram SynthesisSearching Latent Program Spaces
Program synthesis methods aim to automatically generate programs restricted to a language that can explain a given specification of input-output pairs. While purely symbolic approaches suffer from a combinatorial search …
ARCProgram inductionProgram SynthesisTest-time AdaptationLLMPhy: Complex Physical Reasoning Using Large Language Models and World Models
Physical reasoning is an important skill needed for robotic agents when operating in the real world. However, solving such reasoning problems often involves hypothesizing and reflecting over complex multi-body interactio…
FrictionProgram SynthesisThe Surprising Effectiveness of Test-Time Training for Few-Shot Learning
Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples. We investi…
ARCFew-Shot LearningIn-Context LearningLanguage Modeling+2Combining Induction and Transduction for Abstract Reasoning
When learning an input-output mapping from very few examples, is it better to first infer a latent function that explains the examples, or is it better to directly predict new test outputs, e.g. using a neural network? W…
ARCProgram SynthesisReinforcement learning with learned gadgets to tackle hard quantum problems on real hardware
Designing quantum circuits for specific tasks is challenging due to the exponential growth of the state space. We introduce gadget reinforcement learning (GRL), which integrates reinforcement learning with program synthe…
GPUProgram Synthesisreinforcement-learningReinforcement LearningSystem 2 Reasoning via Generality and Adaptation
While significant progress has been made in task-specific applications, current models struggle with deep reasoning, generality, and adaptation -- key components of System 2 reasoning that are crucial for achieving Artif…
Meta-LearningProgram Synthesis