{"total":58,"rows":[{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263,"area":"lr"},{"id":"2508.05748","title":"WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent","created":"2025-08-07","cited_by_count":119,"area":"agents"},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2509.01142","title":"Dream-Coder 7B: An Open Diffusion Language Model for Code","created":"2025-09-01","cited_by_count":81,"area":"diffusion"},{"id":"2511.16043","title":"Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning","created":"2025-11-20","cited_by_count":75,"area":"lr"},{"id":"2603.00729","title":"Qwen3-Coder-Next Technical Report","created":"2026-02-28","cited_by_count":71,"area":"agents"},{"id":"2506.03524","title":"Seed-Coder: Let the Code Model Curate Data for Itself","created":"2025-06-04","cited_by_count":49,"area":null},{"id":"2506.05817","title":"CodeContests+: High-Quality Test Case Generation for Competitive Programming","created":"2025-06-06","cited_by_count":46,"area":"lr"},{"id":"2502.03492","title":"Teaching Language Models to Critique via Reinforcement Learning","created":"2025-02-05","cited_by_count":42,"area":"lr"},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2602.10975","title":"FeatureBench: Benchmarking Agentic Coding for Complex Feature Development","created":"2026-02-11","cited_by_count":34,"area":"agents"},{"id":"2412.11990","title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","created":"2024-12-16","cited_by_count":20,"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":"2506.09003","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","created":"2025-06-10","cited_by_count":20,"area":null},{"id":"2502.19166","title":"CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"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":"2502.16614","title":"CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models","created":"2025-02-23","cited_by_count":14,"area":"lr"},{"id":"2604.10923","title":"Mem$^2$Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation","created":"2026-04-13","cited_by_count":12,"area":"agents"},{"id":"2509.22601","title":"Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning","created":"2025-09-26","cited_by_count":11,"area":"agents"},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2601.04809","title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2603.15611","title":"Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2502.07487","title":"Multi-Agent Collaboration for Multilingual Code Instruction Tuning","created":"2025-02-11","cited_by_count":6,"area":"agents"},{"id":"2512.23966","title":"Efficient Context Scaling with LongCat ZigZag Attention","created":"2025-12-30","cited_by_count":6,"area":null},{"id":"2601.11077","title":"ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development","created":"2026-01-16","cited_by_count":6,"area":"agents"},{"id":"2603.16733","title":"IQuest-Coder-V1 Technical Report","created":"2026-03-17","cited_by_count":6,"area":"agents"},{"id":"2507.22462","title":"IFEvalCode: Controlled Code Generation","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2604.03144","title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2507.05281","title":"CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2509.24239","title":"ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2604.04017","title":"GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces","created":"2026-04-05","cited_by_count":3,"area":"lr"},{"id":"2604.09748","title":"Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward","created":"2026-04-10","cited_by_count":3,"area":"lr"},{"id":"2601.08274","title":"Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2603.10624","title":"Reinforcement Learning with Conditional Expectation Reward","created":"2026-03-11","cited_by_count":2,"area":"lr"},{"id":"2609.05933","title":"Rethinking the Evaluation of Efficiency Methods for Multi-Agent Systems","created":"2026-09-05","cited_by_count":2,"area":"lr"},{"id":"2508.05193","title":"STEPWISE-CODEX-Bench: Evaluating Complex Multi-Function Comprehension and Fine-Grained Execution Reasoning","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.17163","title":"TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2601.14696","title":"AdaTIR: Adaptive Tool-Integrated Reasoning via Difficulty-Aware Policy Optimization","created":"2026-01-21","cited_by_count":1,"area":"lr"},{"id":"2604.27467","title":"ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.13641","title":"Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization","created":"2026-05-13","cited_by_count":1,"area":"deeprl"},{"id":"2605.22138","title":"Efficient Agentic Reasoning Through Self-Regulated Simulative Planning","created":"2026-05-21","cited_by_count":1,"area":"wm"},{"id":"2601.18119","title":"Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2604.02794","title":"CharTool: Tool-Integrated Visual Reasoning for Chart Understanding","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2605.04637","title":"SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2605.14539","title":"Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.22642","title":"Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning","created":"2026-05-21","cited_by_count":0,"area":"agents"},{"id":"2605.28678","title":"DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2606.06178","title":"Learning to Route LLMs from Implicit Cost-Performance Preferences via Meta-Learning","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.19966","title":"Towards Reliable C-to-Rust Translation with Rule-Guided Reasoning and Reinforcement Learning","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2609.12708","title":"What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.27284","title":"Hunyuan-A13B Technical Report","created":"2026-09-23","cited_by_count":0,"area":"moe"},{"id":"2609.33243","title":"CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.02039","title":"CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.04973","title":"TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.17860","title":"Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}