Overview

Program synthesis studies how to turn desired behavior into executable code, from small transformations and algorithms to robot policies and engineering designs. Methods include enumerative and constraint-based search over domain-specific languages, learning programs from input-output examples, and language-model proposals refined through execution, counterexamples, or formal verification. These approaches can produce reusable, inspectable programs and support settings such as CAD, GPU optimization, and verified software; benchmarks such as ARC-AGI, PBEBench, and ProgramBench test how well systems infer behavior and generalize. Systems are increasingly effective when tasks have clear constraints and feedback, but open-ended synthesis remains difficult: plausible code may fail behavioral tests, miss the intended specification, or generalize poorly beyond the examples and search budget.

Latest papers

CardsList

198 papers19 papers in the last four weeks, down 44% on the four weeks before. 0.1% of all new papers.

  1. MobileWeave: Program-First Synthesis of Dependency-Linked Tasks for Training Mobile GUI Agents

    Nov 18, 2026Ziyi He, Xian Wu, Qiyuan Chen +7Mobile GUI AgentsLLM Agent Training

  2. Born for the Task: Rethinking Quantum Chemistry with Foresighted Agentic Computing

    Nov 17, 2026Haozhi Han, Junjie Yang, Ruge Zhang +9Computational Quantum ChemistryProgram Synthesis

  3. Learning from Mutants: Teaching Small Language Models to Synthesise Loop Invariants

    Nov 14, 2026Daragh King, Vasileios KoutavasLLM-Based Program SynthesisProgram Synthesis

  4. AgentSSL: Can MLE Agents Leverage Unlabeled Data?

    Nov 12, 2026Ethan Lin, Akanksha Sarkar, Ziang Liu +2Semi-Supervised LearningAutomated Machine Learning

  5. Ceci n'est pas une pipe -- Toward a Symbolic Solver for the Abstraction and Reasoning Corpus Using Evolutionary Computation

    Nov 10, 2026Luca Favole, Giorgio Mongardi, Giovanni Squillero +1ARC-AGIProgram Synthesis

  6. Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents

    Nov 10, 2026Wenji Fang, Yao Lu, Jinghua Wang +1Electronic Design AutomationSelf-Improving Agents

  7. The Shape of a Program: Path Signatures for Trace-to-Program Induction

    Nov 8, 2026Mohamed Ghanem, Bernd Finkbeinerautomated interpretabilityProgram Synthesis

  8. GOPR-CAD: Graph-of-Operations Progressive Reasoning for CAD Generation

    Nov 8, 2026Yitian Pang, Yifan Li, Xiaowei Yue +1Text-to-CAD GenerationParametric CAD Modeling

  9. Discovering formally verified quantum programs with AI

    Nov 6, 2026Sergey Shirobokov, Ben Jaderberg, Katerina Hristova +22Automated Algorithm DiscoveryProgram Synthesis

  10. Synthesizing symbolic models of human and machine reasoning at scale

    Nov 4, 2026Solim LeGris, Philipp Mondorf, Jinran Jin +3Symbolic ReasoningProgram Synthesis

  11. Measuring Where Intent Gets Lost in Agentic Smart Contract Synthesis

    Oct 27, 2026Abhinav Goel, Agostino Capponi, Alfio Gliozzo +1Agentic Code GenerationProgram Synthesis

  12. Ranking Function Generation with LLMs for Termination

    Oct 26, 2026Rongkang Li, Jiaxin Hu, Taolue Chen +3Program SynthesisLLM-Based Program Synthesis

  13. FlashScript: Compiling Recurring Agent Workflows into Reusable Neuro-Symbolic Programs

    Oct 24, 2026Sadra Sabouri, Hosein Hasanbeig, Adam Sage +6LLM Agent Workflow OptimizationLLM-Based Program Synthesis

  14. AutoFraming: Synthesizing Dynamic Frames of C Code with LLMs

    Oct 21, 2026Han Zhou, Yu Luo, Dianxiang XuProgram SynthesisFormal Verification

  15. Policy Search in Code Space for Multi-Agent Pathfinding

    Oct 19, 2026Matthias Eder, Pantelis Emmanouil, Vivek Farias +7Multi-Agent Path FindingProgram Synthesis

  16. Scaling Online Exploration for Robot Agents

    Oct 15, 2026Runhan Huang, Xiangcheng Zhang, Haoyu Chen +17Robot LearningContinual Robot Learning

  17. Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning

    Oct 14, 2026Fan Huang, Dezhong Tong, Changyu Chen +2Language-Conditioned Robot ManipulationLanguage-Conditioned Robot Control

  18. Write Once, Plan Many: Building Reusable Visual Planning Systems from One Scene

    Oct 13, 2026Ruixiao Yang, Yilun Hao, Mingxin Yu +2Program SynthesisModel-Based Planning

  19. Program Learning with Verifiable Rewards: Distilling Expert Traces into Programs

    Oct 13, 2026Vishvesh Bhat, Muhammad Ahmed Mohsin, Asad AaliLLM Tool UseLLM-Based Program Synthesis

  20. Fly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical Feedback

    Oct 8, 2026Jaewoo Lee, Jeongyeon Seo, Sihyun Cho +10Robotic Program SynthesisError Feedback