{"total":27,"rows":[{"id":"2510.18471","title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","created":"2025-10-21","cited_by_count":24,"area":null},{"id":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23,"area":null},{"id":"2603.19329","title":"Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification","created":"2026-03-18","cited_by_count":11,"area":null},{"id":"2510.06296","title":"VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code","created":"2025-10-07","cited_by_count":7,"area":null},{"id":"2509.23061","title":"Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2601.19001","title":"FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2606.25178","title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2510.08720","title":"How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2604.12268","title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2602.06098","title":"A Theoretical Analysis of Test-Driven Code Generation","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2604.03922","title":"ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation","created":"2026-04-05","cited_by_count":2,"area":null},{"id":"2604.05963","title":"QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2505.23598","title":"LLM Performance for Code Generation on Noisy Tasks","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.15868","title":"Small Edits, Big Consequences: Telling Good from Bad Robustness in Large Language Models","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2601.00575","title":"InfoSynth: Information-Guided Benchmark Synthesis for LLMs","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2605.13280","title":"Characterizing Readability Issue Patterns and the Role of Prompt Design in LLM-Generated Code","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2609.37633","title":"RLTL;DR: Self-improvement by Internalizing Self-generated Feedback","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2512.18131","title":"Holistic Evaluation of State-of-the-Art LLMs for Code Generation","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2601.13995","title":"From Tags to Trees: Structuring Fine-Grained Knowledge for Controllable Data Selection in LLM Instruction Tuning","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2603.04212","title":"Code Fingerprints: Disentangled Attribution of LLM-Generated Code","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.06111","title":"Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.18822","title":"Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.05486","title":"Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.09366","title":"Diversifying to Verify: When Task-Equivalent Programs Differ in Verifiability","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.20764","title":"ArbiGraph: Arbitrarily Scalable Verifiable Task Graphs for Evaluating Context Management","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.37405","title":"Complexity-Aware Evaluation of LLM Comprehension","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02571","title":"Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}