Papers Program Synthesis
“Program Synthesis” 태그가 달린 논문 538편 · 필터 해제
EvolveSignal: A Large Language Model Powered Coding Agent for Discovering Traffic Signal Control Strategies
In traffic engineering, fixed-time traffic signal control remains widely used for its low cost, stability, and interpretability. However, its design relies on hand-crafted formulas (e.g., Webster) and manual re-timing by…
Program SynthesisCausalARC: Abstract Reasoning with Causal World Models
On-the-fly reasoning often requires adaptation to novel problems under limited data and distribution shift. This work introduces CausalARC: an experimental testbed for AI reasoning in low-data and out-of-distribution reg…
Logical ReasoningProgram SynthesisRefineStat: Efficient Exploration for Probabilistic Program Synthesis
Probabilistic programming offers a powerful framework for modeling uncertainty, yet statistical model discovery in this domain entails navigating an immense search space under strict domain-specific constraints. When sma…
Program SynthesisLLM-Generated Explanations Do Not Suffice for Ultra-Strong Machine Learning
Ultra Strong Machine Learning (USML) refers to symbolic learning systems that not only improve their own performance but can also teach their acquired knowledge to quantifiably improve human performance. We introduce LEN…
Program SynthesisActive LearningBenchmarking LLM-based agents for single-cell omics analysis
Background: The surge in single-cell omics data exposes limitations in traditional, manually defined analysis workflows. AI agents offer a paradigm shift, enabling adaptive planning, executable code generation, traceable…
Program SynthesisCode GenerationMiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time
Large language models (LLMs) are increasingly being applied to black-box optimization tasks, from program synthesis to molecule design. Prior work typically leverages in-context learning to iteratively guide the model to…
Program SynthesisChannel-Wise MLPs Improve the Generalization of Recurrent Convolutional Networks
We investigate the impact of channel-wise mixing via multi-layer perceptrons (MLPs) on the generalization capabilities of recurrent convolutional networks. Specifically, we compare two architectures: DARC (Depth Aware Re…
Program SynthesisGP and LLMs for Program Synthesis: No Clear Winners
Genetic programming (GP) and large language models (LLMs) differ in how program specifications are provided: GP uses input-output examples, and LLMs use text descriptions. In this work, we compared the ability of PushGP …
Program SynthesisHyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents
Recent advances in multimodal large language models (MLLMs) have enabled richer perceptual grounding for code policy generation in embodied agents. However, most existing systems lack effective mechanisms to adaptively m…
Multimodal ReasoningRobot ManipulationProgram SynthesisDr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing
Language models for program synthesis are usually trained and evaluated on programming competition datasets (MBPP, APPS). However, these datasets are limited in size and quality, while these language models are extremely…
Reinforcement LearningProgram SynthesisOut-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuning
We run a controlled compositional generalization experiment in the ARC-AGI domain: an open-world problem domain in which the ability to generalize out-of-distribution is, by design, an essential characteristic for succes…
Program SynthesisLLM-Based Config Synthesis requires Disambiguation
Beyond hallucinations, another problem in program synthesis using LLMs is ambiguity in user intent. We illustrate the ambiguity problem in a networking context for LLM-based incremental configuration synthesis of route-m…
Program SynthesisModelling Program Spaces in Program Synthesis with Constraints
A core challenge in program synthesis is taming the large space of possible programs. Since program synthesis is essentially a combinatorial search, the community has sought to leverage powerful combinatorial constraint …
Inductive logic programmingProgram SynthesisSelf-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
Many program synthesis tasks prove too challenging for even state-of-the-art language models to solve in single attempts. Search-based evolutionary methods offer a promising alternative by exploring solution spaces itera…
Test-time AdaptationProgram SynthesisCoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs
Large reasoning models (LRMs) have demonstrated impressive capabilities in domains like mathematics and program synthesis. Despite their strong performance, LRMs often exhibit overthinking -- excessive and redundant reas…
GSM8KMathMathematical ReasoningProgram SynthesisChallenges & Opportunities with LLM-Assisted Visualization Retargeting
Despite the ubiquity of visualization examples published on the web, retargeting existing custom chart implementations to new datasets remains difficult, time-intensive, and tedious. The adaptation process assumes author…
Program SynthesisStructured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge
The IPARC Challenge, inspired by ARC, provides controlled program synthesis tasks over synthetic images to evaluate automatic program construction, focusing on sequence, selection, and iteration. This set of 600 tasks ha…
ARCCode GenerationProgram SynthesisMatching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences
The rise of Large Language Models (LLMs) has driven progress in reasoning tasks -- from program synthesis to scientific hypothesis generation -- yet their ability to handle ranked preferences and structured algorithms in…
Blockingparameter-efficient fine-tuningProgram SynthesisChemical classification program synthesis using generative artificial intelligence
Accurately classifying chemical structures is essential for cheminformatics and bioinformatics, including tasks such as identifying bioactive compounds of interest, screening molecules for toxicity to humans, finding non…
ClassificationDrug DiscoveryProgram SynthesisCLEVER: A Curated Benchmark for Formally Verified Code Generation
We introduce ${\rm C{\small LEVER}}$, a high-quality, curated benchmark of 161 problems for end-to-end verified code generation in Lean. Each problem consists of (1) the task of generating a specification that matches a …
Code GenerationProgram Synthesis