{"total":28,"rows":[{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462,"area":"lr"},{"id":"2209.00840","title":"FOLIO: Natural Language Reasoning with First-Order Logic","created":"2022-09-02","cited_by_count":235,"area":"lr"},{"id":"2507.23370","title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","created":"2025-07-31","cited_by_count":94,"area":"lr"},{"id":"2502.12468","title":"MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation","created":"2025-02-18","cited_by_count":32,"area":"lr"},{"id":"2310.14053","title":"Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain","created":"2023-10-21","cited_by_count":31,"area":"lr"},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2406.13764","title":"Can LLMs Reason in the Wild with Programs?","created":"2024-06-19","cited_by_count":13,"area":"lr"},{"id":"2406.20060","title":"Applying RLAIF for Code Generation with API-usage in Lightweight LLMs","created":"2024-06-28","cited_by_count":10,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2510.18863","title":"EffiReasonTrans: RL-Optimized Reasoning for Code Translation","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2603.02787","title":"Rethinking Code Similarity for Automated Algorithm Design with LLMs","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2410.08437","title":"Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks","created":"2024-10-11","cited_by_count":2,"area":"lr"},{"id":"2505.19502","title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2512.22633","title":"Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair","created":"2025-12-27","cited_by_count":2,"area":"lr"},{"id":"2604.18364","title":"Training and Agentic Inference Strategies for LLM-based Manim Animation Generation","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2504.17665","title":"Evaluating Intermediate Reasoning of Code-Assisted Large Language Models for Mathematics","created":"2025-04-24","cited_by_count":1,"area":"lr"},{"id":"2508.09537","title":"From Context to Intent: Reasoning-Guided Function-Level Code Completion","created":"2025-08-13","cited_by_count":1,"area":"lr"},{"id":"2509.09942","title":"Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2601.07280","title":"ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2607.21971","title":"Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning","created":"2026-07-24","cited_by_count":1,"area":"lr"},{"id":"2509.05553","title":"Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study","created":"2025-09-06","cited_by_count":0,"area":"lr"},{"id":"2511.06522","title":"FractalBench: Diagnosing Visual-Mathematical Reasoning Through Recursive Program Synthesis","created":"2025-11-09","cited_by_count":0,"area":"lr"},{"id":"2603.18334","title":"Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2608.17414","title":"REChart: Reasoning-Efficient Chart Editing with Large Reasoning Models","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2608.18111","title":"Solving Is Not Drawing: A Benchmark for Diagrammatic Reasoning in Olympiad Geometry","created":"2026-06-23","cited_by_count":0,"area":"lr"},{"id":"2608.25775","title":"ToST: A Tree-of-Thought Socratic Teaching Framework for Multi-Path Guidance and Parallel Thinking","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.17708","title":"Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents","created":"2026-09-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}