{"total":59,"rows":[{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462,"area":"lr"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358,"area":null},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353,"area":null},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312,"area":"lr"},{"id":"2310.10021","title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","created":"2023-10-16","cited_by_count":86,"area":"synth"},{"id":"2405.15383","title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","created":"2024-05-24","cited_by_count":40,"area":"wm"},{"id":"2402.19299","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy","created":"2024-02-29","cited_by_count":32,"area":null},{"id":"2403.17246","title":"TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models","created":"2024-03-25","cited_by_count":29,"area":"agents"},{"id":"2309.01038","title":"Neurosymbolic Reinforcement Learning and Planning: A Survey","created":"2023-09-02","cited_by_count":24,"area":null},{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"area":"deeprl"},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21,"area":null},{"id":"2301.12950","title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs","created":"2023-01-30","cited_by_count":20,"area":null},{"id":"2402.08280","title":"Pix2Code: Learning to Compose Neural Visual Concepts as Programs","created":"2024-02-13","cited_by_count":18,"area":null},{"id":"2405.16450","title":"Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"2311.02104","title":"Efficient Symbolic Policy Learning with Differentiable Symbolic Expression","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2401.03188","title":"A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence","created":"2024-01-06","cited_by_count":10,"area":null},{"id":"2510.12088","title":"One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration","created":"2025-10-14","cited_by_count":10,"area":"wm"},{"id":"2304.03767","title":"Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Following","created":"2023-04-07","cited_by_count":9,"area":null},{"id":"2205.01265","title":"From {Solution Synthesis} to {Student Attempt Synthesis} for Block-Based Visual Programming Tasks","created":"2022-05-03","cited_by_count":8,"area":null},{"id":"2406.02791","title":"Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedback","created":"2024-06-04","cited_by_count":8,"area":null},{"id":"2508.05433","title":"Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies","created":"2025-08-07","cited_by_count":8,"area":"mllm"},{"id":"2508.19506","title":"Learning Game-Playing Agents with Generative Code Optimization","created":"2025-08-27","cited_by_count":8,"area":"agents"},{"id":"2303.06018","title":"Hierarchical Neural Program Synthesis","created":"2023-03-09","cited_by_count":7,"area":null},{"id":"2510.01272","title":"Modeling Others' Minds as Code","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2304.12090","title":"Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2309.03651","title":"Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments","created":"2023-09-07","cited_by_count":5,"area":null},{"id":"2405.05431","title":"Searching for Programmatic Policies in Semantic Spaces","created":"2024-05-08","cited_by_count":5,"area":null},{"id":"2408.08761","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","created":"2024-08-16","cited_by_count":5,"area":"deeprl"},{"id":"2601.06845","title":"Code Evolution for Control: Synthesizing Policies via LLM-Driven Evolutionary Search","created":"2026-01-11","cited_by_count":4,"area":null},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2303.01440","title":"Programmatic Imitation Learning from Unlabeled and Noisy Demonstrations","created":"2023-03-02","cited_by_count":3,"area":"offlinerl"},{"id":"2503.08322","title":"Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs","created":"2025-03-11","cited_by_count":3,"area":"deeprl"},{"id":"2601.21239","title":"TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Design","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2602.19304","title":"Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation","created":"2026-02-22","cited_by_count":3,"area":"agents"},{"id":"2306.12456","title":"Pushing the Limits of Machine Design: Automated CPU Design with AI","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2408.04336","title":"KnowPC: Knowledge-Driven Programmatic Reinforcement Learning for Zero-shot Coordination","created":"2024-08-08","cited_by_count":2,"area":"deeprl"},{"id":"2410.12166","title":"Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2505.12508","title":"InnateCoder: Learning Programmatic Options with Foundation Models","created":"2025-05-18","cited_by_count":2,"area":"deeprl"},{"id":"2606.16496","title":"REFLEX: Reflective Evolution from LLM Experience","created":"2026-06-15","cited_by_count":2,"area":"mllm"},{"id":"2310.05178","title":"Optimizing Large Language Models to Expedite the Development of Smart Contracts","created":"2023-10-08","cited_by_count":1,"area":null},{"id":"2310.11614","title":"Learning a Hierarchical Planner from Humans in Multiple Generations","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2311.15960","title":"Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2402.05307","title":"Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2407.14714","title":"Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming","created":"2024-07-20","cited_by_count":1,"area":"deeprl"},{"id":"2410.21940","title":"Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution","created":"2024-10-29","cited_by_count":1,"area":"deeprl"},{"id":"2506.20097","title":"PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Models","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2603.28386","title":"COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2202.13040","title":"Iterative Genetic Improvement: Scaling Stochastic Program Synthesis","created":"2022-02-26","cited_by_count":0,"area":null},{"id":"2307.15456","title":"Worrisome Properties of Neural Network Controllers and Their Symbolic Representations","created":"2023-07-28","cited_by_count":0,"area":null},{"id":"2411.00139","title":"Learning local discrete features in explainable-by-design convolutional neural networks","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2506.14162","title":"Common Benchmarks Undervalue the Generalization Power of Programmatic Policies","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2509.10973","title":"Decoupling Search and Learning in Neural Net Training","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2601.04365","title":"Survival Dynamics of Neural and Programmatic Policies in Evolutionary Reinforcement Learning","created":"2026-01-07","cited_by_count":0,"area":"deeprl"},{"id":"2605.17137","title":"Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.18454","title":"Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2605.18508","title":"DiPRL: Learning Discrete Programmatic Policies via Architecture Entropy Regularization","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2606.19741","title":"Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.03461","title":"Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer","created":"2026-08-04","cited_by_count":0,"area":null}],"next_cursor":null}