{"total":62,"rows":[{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2505.20411","title":"SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents","created":"2025-05-26","cited_by_count":142,"area":"agents"},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119,"area":"lr"},{"id":"2501.01257","title":"CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings","created":"2025-01-02","cited_by_count":115,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2509.01322","title":"LongCat-Flash Technical Report","created":"2025-09-01","cited_by_count":58,"area":"agents"},{"id":"2411.12882","title":"ProSec: Fortifying Code LLMs with Proactive Security Alignment","created":"2024-11-19","cited_by_count":25,"area":"alignment"},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2512.16676","title":"DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI","created":"2025-12-18","cited_by_count":23,"area":null},{"id":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","cited_by_count":21,"area":"lr"},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2501.04694","title":"EpiCoder: Encompassing Diversity and Complexity in Code Generation","created":"2025-01-08","cited_by_count":20,"area":null},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2504.10046","title":"GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation","created":"2025-04-14","cited_by_count":17,"area":"rag"},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"id":"2512.18160","title":"Propose, Solve, Verify: Self-Play Through Formal Verification","created":"2025-12-20","cited_by_count":13,"area":"synth"},{"id":"2506.00419","title":"Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences","created":"2025-05-31","cited_by_count":10,"area":"alignment"},{"id":"2411.13611","title":"DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs","created":"2024-11-20","cited_by_count":9,"area":"alignment"},{"id":"2502.13820","title":"Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning","created":"2025-02-19","cited_by_count":9,"area":"lr"},{"id":"2502.09183","title":"RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation","created":"2025-02-13","cited_by_count":8,"area":"lr"},{"id":"2507.13290","title":"Towards Formal Verification of LLM-Generated Code from Natural Language Prompts","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2503.10452","title":"DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation","created":"2025-03-13","cited_by_count":7,"area":null},{"id":"2504.04699","title":"R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation","created":"2025-04-07","cited_by_count":7,"area":"lr"},{"id":"2602.07422","title":"Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model","created":"2026-02-07","cited_by_count":6,"area":"alignment"},{"id":"2503.05507","title":"Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?","created":"2025-03-07","cited_by_count":5,"area":null},{"id":"2504.10557","title":"The Code Barrier: What LLMs Actually Understand?","created":"2025-04-14","cited_by_count":5,"area":null},{"id":"2505.15874","title":"Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2507.22080","title":"CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback","created":"2025-07-25","cited_by_count":5,"area":null},{"id":"2508.04865","title":"Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment","created":"2025-08-06","cited_by_count":5,"area":null},{"id":"2509.21891","title":"AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans","created":"2025-09-26","cited_by_count":5,"area":"agents"},{"id":"2605.02944","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2605.16299","title":"ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization","created":"2026-04-17","cited_by_count":4,"area":"alignment"},{"id":"2606.01286","title":"BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution","created":"2026-05-31","cited_by_count":4,"area":null},{"id":"2606.07909","title":"MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback","created":"2026-06-06","cited_by_count":4,"area":"agents"},{"id":"2502.11466","title":"GiFT: Gibbs Fine-Tuning for Code Generation","created":"2025-02-17","cited_by_count":3,"area":null},{"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":"2510.23208","title":"Increasing LLM Coding Capabilities through Diverse Synthetic Coding Tasks","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2603.15159","title":"To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2502.11901","title":"Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2509.19918","title":"Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation","created":"2025-09-24","cited_by_count":2,"area":"agents"},{"id":"2509.25203","title":"Generating High-Quality Datasets for Code Editing via Open-Source Language Models","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2606.28438","title":"When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs","created":"2026-06-26","cited_by_count":2,"area":"synth"},{"id":"2608.13566","title":"Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2505.14597","title":"Success is in the Details: Evaluate and Enhance Details Sensitivity of Code LLMs through Counterfactuals","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2505.18789","title":"From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2508.08680","title":"TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2509.20837","title":"Verification Limits Code LLM Training","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2510.16022","title":"Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2601.06953","title":"X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2603.29292","title":"Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2604.05100","title":"Edit, But Verify: An Empirical Audit of Instructed Code-Editing Benchmarks","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2606.18286","title":"CODEBLOCK: Learning to Supervise Code at the Right Granularity","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2512.21580","title":"Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLM","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2602.02554","title":"BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2606.28998","title":"Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2606.29097","title":"TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2607.07619","title":"Rethinking Code Performance Benchmarks for LLMs","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2607.14735","title":"CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA","created":"2026-07-16","cited_by_count":0,"area":"lr"},{"id":"2609.22102","title":"When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2610.18004","title":"SWEPatchTest: Evaluating Software Tests Beyond Reproduction","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}