{"total":63,"rows":[{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2411.00622","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","created":"2024-11-01","cited_by_count":61,"area":"agents"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2502.03492","title":"Teaching Language Models to Critique via Reinforcement Learning","created":"2025-02-05","cited_by_count":42,"area":"lr"},{"id":"2602.04837","title":"Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing","created":"2026-02-04","cited_by_count":36,"area":"synth"},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2505.22411","title":"Mitigating Overthinking in Large Reasoning Models via Manifold Steering","created":"2025-05-28","cited_by_count":33,"area":"lr"},{"id":"2410.08105","title":"What Makes Large Language Models Reason in (Multi-Turn) Code Generation?","created":"2024-10-10","cited_by_count":29,"area":"lr"},{"id":"2502.20380","title":"Multi-Turn Code Generation Through Single-Step Rewards","created":"2025-02-27","cited_by_count":28,"area":"alignment"},{"id":"2407.16732","title":"PyBench: Evaluating LLM Agent on various real-world coding tasks","created":"2024-07-23","cited_by_count":24,"area":"agents"},{"id":"2502.12466","title":"EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking","created":"2025-02-18","cited_by_count":24,"area":"lr"},{"id":"2502.01619","title":"Learning to Generate Unit Tests for Automated Debugging","created":"2025-02-03","cited_by_count":17,"area":null},{"id":"2506.15655","title":"cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree","created":"2025-06-18","cited_by_count":17,"area":"rag"},{"id":"2503.23145","title":"CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis","created":"2025-03-29","cited_by_count":16,"area":"lr"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2504.14119","title":"CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning","created":"2025-04-19","cited_by_count":14,"area":"lr"},{"id":"2503.07358","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2503.05703","title":"What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces","created":"2025-02-10","cited_by_count":12,"area":null},{"id":"2411.13941","title":"LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues","created":"2024-11-21","cited_by_count":10,"area":null},{"id":"2409.19715","title":"Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code","created":"2024-09-29","cited_by_count":9,"area":"alignment"},{"id":"2406.12276","title":"CodeNav: Beyond tool-use to using real-world codebases with LLM agents","created":"2024-06-18","cited_by_count":8,"area":"agents"},{"id":"2501.16456","title":"CoCoNUT: Structural Code Understanding does not fall out of a tree","created":"2025-01-27","cited_by_count":7,"area":null},{"id":"2501.18482","title":"A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models","created":"2025-01-30","cited_by_count":7,"area":"lr"},{"id":"2503.19599","title":"HoarePrompt: Structural Reasoning About Program Correctness in Natural Language","created":"2025-03-25","cited_by_count":7,"area":"lr"},{"id":"2504.07634","title":"Agent That Debugs: Dynamic State-Guided Vulnerability Repair","created":"2025-04-10","cited_by_count":7,"area":"agents"},{"id":"2411.05199","title":"CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2510.03415","title":"LLMs Lean on Priors, Not Programming Language Semantics","created":"2025-10-03","cited_by_count":6,"area":"lr"},{"id":"2603.11226","title":"ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning","created":"2026-03-11","cited_by_count":6,"area":"lr"},{"id":"2503.13992","title":"The KoLMogorov Test: Compression by Code Generation","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2503.22832","title":"L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution","created":"2025-03-28","cited_by_count":5,"area":"lr"},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2504.11711","title":"The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs","created":"2025-04-16","cited_by_count":4,"area":null},{"id":"2505.17703","title":"Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2507.17548","title":"CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning","created":"2025-07-23","cited_by_count":4,"area":"lr"},{"id":"2509.26546","title":"Towards Verified Code Reasoning by LLMs","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2509.11686","title":"Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2603.02787","title":"Rethinking Code Similarity for Automated Algorithm Design with LLMs","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2604.16243","title":"Find, Fix, Reason: Context Repair for Video Reasoning","created":"2026-04-17","cited_by_count":3,"area":"mllm"},{"id":"2509.22546","title":"Think Socially via Cognitive Reasoning","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2601.11658","title":"Towards AGI A Pragmatic Approach Towards Self Evolving Agent","created":"2026-01-15","cited_by_count":2,"area":"agents"},{"id":"2605.11922","title":"StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning","created":"2026-05-12","cited_by_count":2,"area":"alignment"},{"id":"2406.04710","title":"Morescient GAI for Software Engineering (Extended Version)","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2503.08228","title":"Investigating Execution-Aware Language Models for Code Optimization","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2507.05065","title":"Replacing thinking with tool usage enables reasoning in small language models","created":"2025-07-07","cited_by_count":1,"area":"lr"},{"id":"2603.09951","title":"Towards a Neural Debugger for Python","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2605.09186","title":"Agentic MIP Research: Accelerated Constraint Handler Generation","created":"2026-05-09","cited_by_count":1,"area":"agents"},{"id":"2503.22388","title":"Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2512.00127","title":"Generating Verifiable Chain of Thoughts from Exection-Traces","created":"2025-11-28","cited_by_count":0,"area":"lr"},{"id":"2603.13640","title":"SemRep: Generative Code Representation Learning with Code Transformations","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.07755","title":"An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.06184","title":"Teaching LLMs Program Semantics via Symbolic Execution Traces","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.17444","title":"MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair","created":"2026-05-17","cited_by_count":0,"area":"agents"},{"id":"2606.07665","title":"AgentCompile: An LLM-Guided Compiler for Direct CUDA Inference","created":"2026-06-04","cited_by_count":0,"area":"inference"},{"id":"2606.29742","title":"MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice Decomposition","created":"2026-06-29","cited_by_count":0,"area":"agents"},{"id":"2609.00579","title":"Predicting Program Exit Code with LLMs and Programming Language Semantics","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.26388","title":"On the Lexical Superstition of Large Language Models for Code Comprehension: Re-evaluation on Code of Low Lexical Quality","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.34359","title":"Improving Large Language Models for Code through Runtime Program-State Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.39022","title":"From Verification Failures to Reusable Guidance for Coding Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.04737","title":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.15368","title":"ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs","created":"2026-10-11","cited_by_count":0,"area":"wm"}],"next_cursor":null}