Papers Program Synthesis
“Program Synthesis” 태그가 달린 논문 538편 · 필터 해제
Vector Symbolic Algebras for the Abstraction and Reasoning Corpus
The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) is a generative, few-shot fluid intelligence benchmark. Although humans effortlessly solve ARC-AGI, it remains extremely difficult for ev…
Program SynthesisFractalBench: Diagnosing Visual-Mathematical Reasoning Through Recursive Program Synthesis
Mathematical reasoning requires abstracting symbolic rules from visual patterns -- inferring the infinite from the finite. We investigate whether multimodal AI systems possess this capability through FractalBench, a benc…
Mathematical ReasoningProgram SynthesisVCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis and debugging, leaving visual-centric c…
Program SynthesisCode GenerationTowards a Measure of Algorithm Similarity
Given two algorithms for the same problem, can we determine whether they are meaningfully different? In full generality, the question is uncomputable, and empirically it is muddied by competing notions of similarity. Yet…
Program SynthesisBridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with Bézier Curves
While Vision-language Models (VLMs) have demonstrated strong semantic capabilities, their ability to interpret the underlying geometric structure of visual information is less explored. Pictographic characters, which com…
Program SynthesisOnce Upon an Input: Reasoning via Per-Instance Program Synthesis
Large language models (LLMs) excel at zero-shot inference but continue to struggle with complex, multi-step reasoning. Recent methods that augment LLMs with intermediate reasoning steps such as Chain of Thought (CoT) and…
Visual Question AnsweringMathematical ReasoningRelational ReasoningProgram SynthesisHey Pentti, We Did It Again!: Differentiable vector-symbolic types that prove polynomial termination
We present a typed computer language, Doug, in which all typed programs may be proved to halt in polynomial time, encoded in a vector-symbolic architecture (VSA). Doug is just an encoding of the light linear functional p…
Program SynthesisLearning to Guarantee Type Correctness in Code Generation through Type-Guided Program Synthesis
Language models have shown remarkable proficiency in code generation; nevertheless, ensuring type correctness remains a challenge. Although traditional methods, such as constrained decoding, alleviate this problem by ext…
Program SynthesisCode GenerationHerb.jl: A Unifying Program Synthesis Library
Program synthesis -- the automatic generation of code given a specification -- is one of the most fundamental tasks in artificial intelligence (AI) and the dream of many programmers. Numerous synthesizers have been devel…
Program SynthesisLLM-Guided Evolutionary Program Synthesis for Quasi-Monte Carlo Design
Low-discrepancy point sets and digital sequences underpin quasi-Monte Carlo (QMC) methods for high-dimensional integration. We cast two long-standing QMC design problems as program synthesis and solve them with an LLM-gu…
Program SynthesisCombining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis
Large Language models (LLMs) have shown promise as generators of symbolic control policies, producing interpretable program-like representations through iterative search. However, these models are not capable of separati…
Program SynthesisInteractive Program Synthesis for Modeling Collaborative Physical Activities from Narrated Demonstrations
Teaching systems physical tasks is a long standing goal in HCI, yet most prior work has focused on non collaborative physical activities. Collaborative tasks introduce added complexity, requiring systems to infer users a…
Program SynthesisModeling Others' Minds as Code
Accurate prediction of human behavior is essential for robust and safe human-AI collaboration. However, existing approaches for modeling people are often data-hungry and brittle because they either make unrealistic assum…
Action UnderstandingProgram SynthesisMultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models
Material node graphs are programs that generate the 2D channels of procedural materials, including geometry such as roughness and displacement maps, and reflectance such as albedo and conductivity maps. They are essentia…
Program SynthesisA benchmark for vericoding: formally verified program synthesis
We present and test the largest benchmark for vericoding, LLM-generation of formally verified code from formal specifications - in contrast to vibe coding, which generates potentially buggy code from a natural language d…
Program SynthesisAutomated Multi-Agent Workflows for RTL Design
The rise of agentic AI workflows unlocks novel opportunities for computer systems design and optimization. However, for specialized domains such as program synthesis, the relative scarcity of HDL and proprietary EDA reso…
Program SynthesisCode GenerationProgram Synthesis via Test-Time Transduction
We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly leverages test inputs during synthesis. While prior approaches to program synthesis--whether based on natural l…
Program SynthesisActive LearningREAMS: Reasoning Enhanced Algorithm for Maths Solving
The challenges of solving complex university-level mathematics problems, particularly those from MIT, and Columbia University courses, and selected tasks from the MATH dataset, remain a significant obstacle in the field …
Mathematical ReasoningZero-Shot LearningProgram SynthesisHow are Scientific Concepts Birthed? Typing Rules of Concept Formation in Theoretical Physics Reasoning
This work aims to formalize some of the ways scientific concepts are formed in the process of theoretical physics discovery. Since this may at first seem like a task beyond the scope of the exact sciences (natural and fo…
Program SynthesisSymbolic Graphics Programming with Large Language Models
Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored. We study symbolic graphics programmin…
Reinforcement LearningProgram Synthesis