Papers Program Synthesis
“Program Synthesis” 태그가 달린 논문 538편 · 필터 해제
Coding Agents for Generalized Task and Motion Planning Problems
Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints. Generalize…
Program SynthesisMotion PlanningCommerceVibe: Learning to Design E-Commerce Creatives as Executable Visual Code via Dual-Feedback Reinforcement Learning
High-quality e-commerce creatives are essential for presenting products and conveying marketing messages. Recent diffusion models enable scalable creative generation and produce visually compelling images, but their flat…
Reinforcement LearningProgram SynthesisNarcissus: Program Synthesis Using Context-Aware LLM Approximations
Large language models (LLMs) excel at programming, but not when the task fixes the target language: prompted with a grammar rare in their training data, their programs usually break the grammar or fail the given specific…
Program SynthesisLossless Tensor Compression as Program Synthesis
Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requirements but ignore tensor structure, whereas …
Program SynthesisImage GenerationWeights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
Robot learning is splitting into two bets: policies that bake competence into frozen weights (vision-language-action, or VLA, models), and agents that write and refine their own executable skills as code. This survey org…
Program SynthesisSpecification-Guided Synthesis of Deadlock-Free Communication Protocol Refinements with Large Language Models
Ensuring behavioural correctness in communication protocols is a central challenge in distributed software systems, as subtle inconsistencies can lead to deadlocks. In such settings, protocol refinement - the safe substi…
Program SynthesisCode GenerationSpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch
LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a program from scratch remains fundamentally harder. Recent benchmarks such as ProgramBench quantify this…
Program SynthesisMindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation. However, constructing a complete program from scratch remains a …
Program SynthesisTopoFE: topology-aware LLM-guided Automated Feature Engineering
Automatic feature engineering (AutoFE) for tabular learning can be naturally formulated as a program synthesis problem, where the objective is to discover predictive feature transformations from an exponentially large se…
Feature EngineeringProgram SynthesisGold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text
Financial question answering over hybrid tabular and textual data may require multi-source reasoning and precise numerical computation. While large language models (LLMs) can generate intermediate reasoning steps, natura…
Question AnsweringProgram SynthesisProgram-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 SynthesisARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints. ARCANA decomposes each task into iterative perception, hypothesis generation, symbolic…
Program SynthesisEEG-SpikeAgent: Agentic Closed-Loop Program Synthesis for Automated EEG Spike Detection
Automated detection of interictal epileptiform discharges in scalp electroencephalography (EEG) is clinically important, but recent high-performing deep-learning models often trade interpretability for accuracy. We intro…
Feature EngineeringProgram SynthesisSafe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model
As the scale and complexity of cloud-based AI systems continue to escalate, ensuring service reliability through rapid fault detection and adaptive recovery has become a critical challenge. While existing approaches inte…
Reinforcement LearningProgram SynthesisCOCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives
While interpretable models such as concept bottleneck models (CBMs) and program synthesis methods enable verification of model decisions, their evaluation is typically limited to simple tasks, leaving complex reasoning o…
Program SynthesisAlgoEvolve: LLM-driven Meta-evolution of Algorithmic Trading Programs
Recent work shows that Large Language Models (LLMs) can act as semantic mutation operators for the evolutionary discovery of programs and proofs. Most current applications focus on static coding benchmarks. We extend thi…
Program SynthesisAxon: A Synthesizing Superoptimizer for Tensor Programs
Writing high performance kernels for AI accelerators requires deep expertise in tiling, instruction selection, data layout, and operator fusion placing a significant burden on programmers. In this paper, we focus on tile…
Program SynthesisExplaining Attention with Program Synthesis
A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions. In this paper, we propose an approach for approximating the behavior of…
Question AnsweringProgram SynthesisFllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories
Parametric computer-aided design records both final geometry and the ordered construction history that determines how a part can be edited. Datasets for editable CAD research should therefore expose modeling operations, …
CAD ReconstructionProgram SynthesisPoint CloudsKnow Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning
Large Language Models (LLMs) achieve strong performance on reasoning tasks, but whether this reflects faithful logical inference or heuristic approximation remains unclear. We study this question in legal entailment by c…
Program SynthesisLegal Reasoning