{"total":23,"rows":[{"id":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33,"area":null},{"id":"2406.08316","title":"Is Programming by Example solved by LLMs?","created":"2024-06-12","cited_by_count":27,"area":null},{"id":"2602.17016","title":"M2F: Automated Formalization of Mathematical Literature at Scale","created":"2026-02-19","cited_by_count":15,"area":null},{"id":"2505.02216","title":"LLM-Guided Probabilistic Program Induction for POMDP Model Estimation","created":"2025-05-04","cited_by_count":12,"area":null},{"id":"2511.00162","title":"ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus","created":"2025-10-31","cited_by_count":10,"area":null},{"id":"2508.13876","title":"Improved Generalized Planning with LLMs through Strategy Refinement and Reflection","created":"2025-08-19","cited_by_count":7,"area":null},{"id":"2511.16004","title":"InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution","created":"2025-11-20","cited_by_count":7,"area":null},{"id":"2408.12212","title":"Relational decomposition for program synthesis","created":"2024-08-22","cited_by_count":6,"area":null},{"id":"2604.10508","title":"How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarks","created":"2026-04-12","cited_by_count":5,"area":null},{"id":"2509.17393","title":"Program Synthesis via Test-Time Transduction","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2601.21522","title":"More Bang for the Buck: Improving the Inference of Large Language Models at a Fixed Budget using Reset and Discard (ReD)","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2605.23966","title":"TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2601.12945","title":"A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Bandits","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2607.04537","title":"Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse","created":"2026-07-05","cited_by_count":1,"area":null},{"id":"2609.03955","title":"Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2410.07866","title":"System 2 Reasoning for Human-AI Alignment: Generality and Adaptivity via ARC-AGI","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2505.13249","title":"RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Models","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2511.00160","title":"What a diff makes: automating code migration with large language models","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2603.13640","title":"SemRep: Generative Code Representation Learning with Code Transformations","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2608.06750","title":"Progressive Content Refinement with Decaying Reward Joint LinUCB","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.24545","title":"Discovering Adaptive Transmission Programs for Collective Innovation","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.15094","title":"Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.15894","title":"Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}