Papers Program Synthesis
“Program Synthesis” 태그가 달린 논문 538편 · 필터 해제
Counterexample Guided Learning in the Large using Reasoning Agents
LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-specific, and difficult to control. We approach this challenge by asking…
Program SynthesisBridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization
Precise parametric control over circuit geometry is essential for semiconductor inspection, yet obtaining sufficient real training data remains costly. Although generative models such as diffusion models and Generative A…
Program SynthesisHealthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response
Healthcare mechanisms are inseparable from the strategic provider response they induce: existing healthcare AI benchmarks hold this response fixed and so cannot evaluate mechanisms by the equilibrium they produce. We rec…
Program SynthesisCode SearchFighting Numerical Hallucinations via Data-centric Compilation for Online Financial QA
Large Language Models (LLMs) have significantly advanced online data services, particularly in the domain of financial question answering (FinQA). However, such systems remain susceptible to numerical reasoning hallucina…
Question AnsweringProgram SynthesisHypothesis Generation and Inductive Inference in Children and Language Models
Real world decision-making requires constructing mental models under uncertainty over evidence, over the underlying causal rules, and over the state of the world itself. Which computational principles underpin human infe…
Program SynthesisDomain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards
Large language models show strong potential for automated code generation, but lack guarantees for correctness, quality, safety, and domain-specific constraints. For instance in robotics, where code generation is increas…
Reinforcement LearningProgram SynthesisCode GenerationA-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback
Large Language Models (LLMs) demonstrate strong potential for automated code generation, yet their ability to iteratively refine solutions using execution feedback remains underexplored. Competitive programming offers an…
Program SynthesisCode GenerationThe IsalProgram Programming Language
We introduce IsalProgram (Instruction Set and Language for Programming), a novel assembly-like programming language with three distinctive theoretical properties: (1) it is a regular language in the sense of formal langu…
Program SynthesisProperty-Guided LLM Program Synthesis for Planning
LLMs have shown impressive success in program synthesis, discovering programs that surpass prior solutions. However, these approaches rely on simple numeric scores to signal program quality, such as the value of the solu…
Program SynthesisSolvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
Large language models (LLMs) still struggle with the rigorous reasoning demands of hard competitive programming. While recent multi-agent frameworks attempt to bridge this reliability gap, they remain fundamentally state…
Reinforcement LearningProgram SynthesisRetrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has become a standard approach for knowledge-intensive question answering, but existing systems remain brittle on multi-hop questions, where solving the task requires chaining multipl…
Multi-hop Question AnsweringProgram SynthesisProtocol-Driven Development: Governing Generated Software Through Invariants and Continuous Evidence
Automated program synthesis lowers the cost of producing implementations but introduces a harder governance problem: determining which generated artifacts are admissible. Natural-language specifications are ambiguous, an…
Program SynthesisProspective Compression in Human Abstraction Learning
A core challenge in program synthesis is online library learning: the incremental acquisition of reusable abstractions under uncertainty about future task demands. Existing algorithms treat library learning as retrospect…
Program SynthesisBenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD
Industrial Computer-Aided Design (CAD) code generation requires models to produce executable parametric programs from visual or textual inputs. Beyond recognizing the outer shape of a part, this task involves understandi…
Visual Question AnsweringReinforcement LearningProgram SynthesisCode GenerationBeyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph
Direct Preference Optimization (DPO) aligns language models using pairwise preference comparisons, offering a simple and effective alternative to Reinforcement Learning (RL) from human feedback. However, in many practica…
Reinforcement LearningProgram SynthesisVeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation
Large language models can generate useful code from natural language, but their outputs come without correctness guarantees. Verifiable code generation offers a path beyond testing by requiring models to produce not only…
Program SynthesisCode GenerationReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis
LLMs can solve program synthesis tasks but remain inefficient and unreliable on hard instances requiring large combinatorial search. Given a small set of reasoning traces, we use coding agents to compile them into reusab…
Program SynthesisBeyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis
Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whet…
Program SynthesisAutomated Adversarial Collaboration for Advancing Theory Building in the Cognitive Sciences
Cognitive science often evaluates theories through narrow paradigms and local model comparisons, limiting the integration of evidence across tasks and realizations. We introduce an automated adversarial collaboration fra…
Program SynthesisGradient-Based Program Synthesis with Neurally Interpreted Languages
A central challenge in program induction has long been the trade-off between symbolic and neural approaches. Symbolic methods offer compositional generalisation and data efficiency, yet their scalability is constrained b…
Test-time AdaptationProgram Synthesis