Papers Program Synthesis
“Program Synthesis” 태그가 달린 논문 538편 · 필터 해제
A Small-Scale System for Autoregressive Program Synthesis Enabling Controlled Experimentation
What research can be pursued with small models trained to complete true programs? Typically, researchers study program synthesis via large language models (LLMs) which introduce issues such as knowing what is in or out o…
Instruction FollowingProgram SynthesisAgentic Framework for Epidemiological Modeling
Epidemic modeling is essential for public health planning, yet traditional approaches rely on fixed model classes that require manual redesign as pathogens, policies, and scenario assumptions evolve. We introduce EPIAGEN…
Program SynthesisKAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization
We introduce KAPSO, a modular framework for autonomous program synthesis and optimization. Given a natural language goal and an evaluation method, KAPSO iteratively performs ideation, code synthesis and editing, executio…
Program SynthesisARC Prize 2025: Technical Report
The ARC-AGI benchmark series serves as a critical measure of few-shot generalization on novel tasks, a core aspect of intelligence. The ARC Prize 2025 global competition targeted the newly released ARC-AGI-2 dataset, whi…
Program SynthesisFrom Memorization to Creativity: LLM as a Designer of Novel Neural Architectures
Large language models (LLMs) excel in program synthesis, yet their capacity for neural architecture design -- balancing syntactic reliability, performance, and structural novelty -- remains underexplored. We present a cl…
Program SynthesisOn the Limits of Self-Improving in Large Language Models: The Singularity Is Not Near Without Symbolic Model Synthesis
We formalise recursive self-training in Large Language Models (LLMs) and Generative AI as a discrete-time dynamical system. We prove that if the proportion of exogenous, externally grounded signal $α_t$ vanishes asymptot…
Program SynthesisWebAccessVL: Violation-Aware VLM for Web Accessibility
We present a vision-language model (VLM) that automatically edits website HTML to address violations of the Web Content Accessibility Guidelines 2 (WCAG2) while preserving the original design. We formulate this as a supe…
Program SynthesisFrom User Interface to Agent Interface: Efficiency Optimization of UI Representations for LLM Agents
While Large Language Model (LLM) agents show great potential for automated UI navigation such as automated UI testing and AI assistants, their efficiency has been largely overlooked. Our motivating study reveals that ine…
Program SynthesisEvoLattice: Persistent Internal-Population Evolution through Multi-Alternative Quality-Diversity Graph Representations for LLM-Guided Program Discovery
Large language models (LLMs) are increasingly used to evolve programs and multi-agent systems, yet most existing approaches rely on overwrite-based mutations that maintain only a single candidate at a time. Such methods …
Program SynthesisPRiSM: An Agentic Multimodal Benchmark for Scientific Reasoning via Python-Grounded Evaluation
Evaluating vision-language models (VLMs) in scientific domains like mathematics and physics poses unique challenges that go far beyond predicting final answers. These domains demand conceptual understanding, symbolic rea…
Program SynthesisLAMP: Language-Assisted Motion Planning for Controllable Video Generation
Video generation has achieved remarkable progress in visual fidelity and controllability, enabling conditioning on text, layout, or motion. Among these, motion control - specifying object dynamics and camera trajectories…
Program SynthesisVideo GenerationMotion PlanningFunctional Program Synthesis with Higher-Order Functions and Recursion Schemes
Program synthesis is the process of generating a computer program following a set of specifications, such as a set of input-output examples. It can be modeled as a search problem in which the search space is the set of a…
Program SynthesisAI Co-Artist: A LLM-Powered Framework for Interactive GLSL Shader Animation Evolution
Creative coding and real-time shader programming are at the forefront of interactive digital art, enabling artists, designers, and enthusiasts to produce mesmerizing, complex visual effects that respond to real-time stim…
Program SynthesisEven with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction
Evolutionary program synthesis systems such as AlphaEvolve, OpenEvolve, and ShinkaEvolve offer a new approach to AI-assisted mathematical discovery. These systems utilize teams of large language models (LLMs) to generate…
Program SynthesisBRIDGE: Building Representations In Domain Guided Program Synthesis
Large language models can generate plausible code, but remain brittle for formal verification in proof assistants such as Lean. A central scalability challenge is that verified synthesis requires consistent artifacts acr…
Program SynthesisR3A: Reliable RTL Repair Framework with Multi-Agent Fault Localization and Stochastic Tree-of-Thoughts Patch Generation
Repairing RTL bugs is crucial for hardware design and verification. Traditional automatic program repair (APR) methods define dedicated search spaces to locate and fix bugs with program synthesis. However, they heavily r…
Program SynthesisProgram RepairSynthesizing Visual Concepts as Vision-Language Programs
Vision-Language models (VLMs) achieve strong performance on multimodal tasks but often fail at systematic visual reasoning tasks, leading to inconsistent or illogical outputs. Neuro-symbolic methods promise to address th…
Logical ReasoningProgram SynthesisVisual ReasoningEmpowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learnin…
Reinforcement LearningProgram SynthesisKForge: Program Synthesis for Diverse AI Hardware Accelerators
GPU kernels are critical for ML performance but difficult to optimize across diverse accelerators. We present KForge, a platform-agnostic framework built on two collaborative LLM-based agents: a generation agent that pro…
Program SynthesisAccelerating Training Speed of Tiny Recursive Models with Curriculum Guided Adaptive Recursion
Background: Recursive reasoning models achieve strong performance through iterative refinement, allowing small networks to match large language models. However, training is computationally expensive, often requiring 36 G…
Program Synthesis