{"total":55,"rows":[{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"area":null},{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2510.05094","title":"VChain: Chain-of-Visual-Thought for Reasoning in Video Generation","created":"2025-10-06","cited_by_count":32,"area":null},{"id":"2510.19898","title":"BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills","created":"2025-10-22","cited_by_count":30,"area":null},{"id":"2503.19618","title":"Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data","created":"2025-03-25","cited_by_count":29,"area":null},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2509.22638","title":"Language Models Can Learn from Verbal Feedback Without Scalar Rewards","created":"2025-09-26","cited_by_count":18,"area":null},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16,"area":null},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"area":null},{"id":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2508.20697","title":"Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning","created":"2025-08-28","cited_by_count":8,"area":null},{"id":"2602.03392","title":"On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":8,"area":null},{"id":"2603.23994","title":"Understanding the Challenges in Iterative Generative Optimization with LLMs","created":"2026-03-25","cited_by_count":8,"area":null},{"id":"2506.10954","title":"SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks","created":"2025-06-12","cited_by_count":7,"area":null},{"id":"2505.11480","title":"SuperCoder: Assembly Program Superoptimization with Large Language Models","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2601.13384","title":"From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2602.04811","title":"SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2604.11716","title":"SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context","created":"2026-04-13","cited_by_count":6,"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":"2603.16140","title":"Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards","created":"2026-03-17","cited_by_count":5,"area":null},{"id":"2509.16187","title":"MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2601.13713","title":"SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2601.22859","title":"MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2602.07906","title":"AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering","created":"2026-02-08","cited_by_count":4,"area":null},{"id":"2604.09107","title":"TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training","created":"2026-04-10","cited_by_count":4,"area":null},{"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":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2601.04582","title":"Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2605.09760","title":"ConFit v3: Improving Resume-Job Matching with LLM-based Re-Ranking","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2607.07435","title":"RLVP: Penalize the Path, Reward the Outcome","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2508.03487","title":"BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.20384","title":"R1-Fuzz: Specializing Language Models for Textual Fuzzing via Reinforcement Learning","created":"2025-09-21","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":"2601.20255","title":"HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2603.09951","title":"Towards a Neural Debugger for Python","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2604.00167","title":"A Study on the Impact of Fault localization Granularity for Repository-Scale Code Repair Tasks","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2605.17792","title":"HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2610.10426","title":"CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution","created":"2026-10-07","cited_by_count":1,"area":null},{"id":"2505.24500","title":"TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2509.25716","title":"DeepCodeSeek: Real-Time API Retrieval for Context-Aware Code Generation","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2602.18633","title":"DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning","created":"2026-02-20","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":"2605.00072","title":"XekRung Technical Report","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.00433","title":"Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.05460","title":"Agentic Discovery of Exchange-Correlation Density Functionals","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2607.04577","title":"Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.01422","title":"From Rollouts to Recipes: Self-Contained Post-Training for LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.10123","title":"If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.10315","title":"TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.38606","title":"SecureVibe: Making Vibe Coding More Secure","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.18853","title":"Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19843","title":"LAGO: Language Agents with Reusable Growing Options","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20038","title":"SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}