{"total":130,"rows":[{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2506.20639","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","created":"2025-06-25","cited_by_count":187,"area":"diffusion"},{"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":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2503.02240","title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","created":"2025-03-04","cited_by_count":91,"area":null},{"id":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81,"area":"lr"},{"id":"2506.13284","title":"AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy","created":"2025-06-16","cited_by_count":77,"area":"lr"},{"id":"2512.12730","title":"NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents","created":"2025-12-14","cited_by_count":65,"area":"agents"},{"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":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2502.07316","title":"CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction","created":"2025-02-11","cited_by_count":55,"area":"lr"},{"id":"2504.01934","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement","created":"2025-04-02","cited_by_count":54,"area":null},{"id":"2505.21297","title":"rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset","created":"2025-05-27","cited_by_count":51,"area":"lr"},{"id":"2509.01025","title":"Any-Order Flexible Length Masked Diffusion","created":"2025-08-31","cited_by_count":51,"area":"diffusion"},{"id":"2503.19633","title":"1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training","created":"2025-03-25","cited_by_count":49,"area":"lr"},{"id":"2511.03276","title":"Diffusion Language Models are Super Data Learners","created":"2025-11-05","cited_by_count":48,"area":"diffusion"},{"id":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"id":"2510.01384","title":"Fine-Tuning Masked Diffusion for Provable Self-Correction","created":"2025-10-01","cited_by_count":39,"area":"diffusion"},{"id":"2505.20315","title":"Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL","created":"2025-05-22","cited_by_count":38,"area":"lr"},{"id":"2509.23653","title":"Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models","created":"2025-09-28","cited_by_count":37,"area":"diffusion"},{"id":"2507.15225","title":"Solving Formal Math Problems by Decomposition and Iterative Reflection","created":"2025-07-21","cited_by_count":35,"area":"lr"},{"id":"2510.01329","title":"Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling","created":"2025-10-01","cited_by_count":34,"area":"diffusion"},{"id":"2510.04573","title":"LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning","created":"2025-10-06","cited_by_count":29,"area":"lr"},{"id":"2411.12882","title":"ProSec: Fortifying Code LLMs with Proactive Security Alignment","created":"2024-11-19","cited_by_count":25,"area":"alignment"},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2412.11990","title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","created":"2024-12-16","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":"2501.09213","title":"FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training","created":"2025-01-16","cited_by_count":19,"area":"lr"},{"id":"2509.24007","title":"Sequential Diffusion Language Models","created":"2025-09-28","cited_by_count":19,"area":"diffusion"},{"id":"2602.01326","title":"DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas","created":"2026-02-01","cited_by_count":19,"area":"diffusion"},{"id":"2502.12982","title":"Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2504.17565","title":"DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training","created":"2025-04-24","cited_by_count":18,"area":"lr"},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"area":"alignment"},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2512.13586","title":"ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding","created":"2025-12-15","cited_by_count":18,"area":"diffusion"},{"id":"2504.11109","title":"Agent-Q: Fine-Tuning Large Language Models for Quantum Circuit Generation and Optimization","created":"2025-04-15","cited_by_count":17,"area":"agents"},{"id":"2512.24617","title":"Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space","created":"2025-12-31","cited_by_count":17,"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":"2602.22661","title":"dLLM: Simple Diffusion Language Modeling","created":"2026-02-26","cited_by_count":14,"area":"diffusion"},{"id":"2503.17793","title":"Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM","created":"2025-03-22","cited_by_count":13,"area":"moe"},{"id":"2601.15892","title":"Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model","created":"2026-01-22","cited_by_count":13,"area":null},{"id":"2412.13702","title":"Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models","created":"2024-12-18","cited_by_count":12,"area":"mllm"},{"id":"2508.11953","title":"Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models","created":"2025-08-16","cited_by_count":12,"area":null},{"id":"2511.10192","title":"Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL","created":"2025-11-13","cited_by_count":11,"area":null},{"id":"2501.18858","title":"BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning","created":"2025-01-31","cited_by_count":10,"area":"lr"},{"id":"2510.25510","title":"MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL","created":"2025-10-29","cited_by_count":10,"area":"lr"},{"id":"2504.01986","title":"TuRTLe: A Unified Evaluation of LLMs for RTL Generation","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2509.19894","title":"PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning","created":"2025-09-24","cited_by_count":9,"area":"lr"},{"id":"2510.06499","title":"Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels","created":"2025-10-07","cited_by_count":8,"area":"offlinerl"},{"id":"2508.14727","title":"Assessing the Quality and Security of AI-Generated Code: A Quantitative Analysis","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2605.17283","title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","created":"2026-05-17","cited_by_count":7,"area":"agents"},{"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":"2602.07422","title":"Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model","created":"2026-02-07","cited_by_count":6,"area":"alignment"},{"id":"2603.12529","title":"TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning","created":"2026-03-13","cited_by_count":6,"area":"lr"},{"id":"2604.18224","title":"WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models","created":"2026-04-20","cited_by_count":6,"area":"agents"},{"id":"2501.02795","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","created":"2025-01-06","cited_by_count":5,"area":"lr"},{"id":"2505.16567","title":"Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning","created":"2025-05-22","cited_by_count":5,"area":"safety"},{"id":"2507.18515","title":"A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat","created":"2025-07-24","cited_by_count":5,"area":"rag"},{"id":"2507.20984","title":"SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment","created":"2025-07-28","cited_by_count":5,"area":"lr"},{"id":"2507.22462","title":"IFEvalCode: Controlled Code Generation","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2512.14954","title":"Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation","created":"2025-12-16","cited_by_count":5,"area":"distill"},{"id":"2510.07169","title":"More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning","created":"2025-10-08","cited_by_count":4,"area":"lr"},{"id":"2510.19990","title":"Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond","created":"2025-10-22","cited_by_count":4,"area":"lr"},{"id":"2511.07464","title":"Motif 2 12.7B technical report","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2605.15846","title":"RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades","created":"2026-05-15","cited_by_count":4,"area":"agents"},{"id":"2605.17526","title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","created":"2026-05-17","cited_by_count":4,"area":"agents"},{"id":"2606.06447","title":"Latent Reasoning with Normalizing Flows","created":"2026-06-04","cited_by_count":4,"area":"lr"},{"id":"2505.13098","title":"LLM-KG-Bench 3.0: A Compass for SemanticTechnology Capabilities in the Ocean of LLMs","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2509.25810","title":"Learning to Reason as Action Abstractions with Scalable Mid-Training RL","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2601.19747","title":"Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation","created":"2026-01-27","cited_by_count":3,"area":"agents"},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2603.21465","title":"DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2606.27483","title":"Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning","created":"2026-06-25","cited_by_count":3,"area":"wm"},{"id":"2502.11573","title":"InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2505.11441","title":"Is Compression Really Linear with Code Intelligence?","created":"2025-05-16","cited_by_count":2,"area":null},{"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":"2506.10401","title":"HPCTransCompile: An AI Compiler Generated Dataset for High-Performance CUDA Transpilation and LLM Preliminary Exploration","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2507.06013","title":"CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation","created":"2025-07-08","cited_by_count":2,"area":"lr"},{"id":"2510.06548","title":"Reusing Overtrained Language Models Saturates Scaling","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2602.00747","title":"Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2603.03683","title":"CONCUR: Benchmarking LLMs for Concurrent Code Generation","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2603.15803","title":"Mask Is What DLLM Needs: A Masked Data Training Paradigm for Diffusion LLMs","created":"2026-03-16","cited_by_count":2,"area":"diffusion"},{"id":"2604.10480","title":"Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs","created":"2026-04-12","cited_by_count":2,"area":"agents"},{"id":"2606.13565","title":"A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding","created":"2026-06-11","cited_by_count":2,"area":"diffusion"},{"id":"2606.19535","title":"FloatDoor: Platform-Triggered Backdoors in LLMs","created":"2026-06-17","cited_by_count":2,"area":"safety"},{"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":"2607.17620","title":"PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2502.18515","title":"Securing Smart Contract Languages with a Unified Agentic Framework for Vulnerability Repair in Solidity and Move","created":"2025-02-22","cited_by_count":1,"area":"agents"},{"id":"2504.09639","title":"Leveraging Reasoning Model Answers to Enhance Non-Reasoning Model Capability","created":"2025-04-13","cited_by_count":1,"area":"lr"},{"id":"2505.02142","title":"Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study","created":"2025-05-04","cited_by_count":1,"area":"lr"},{"id":"2505.05063","title":"CodeMixBench: Evaluating Large Language Models on Code Generation with Code-Mixed Prompts","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2505.13766","title":"A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.17639","title":"PreMoE: Proactive Inference for Efficient Mixture-of-Experts","created":"2025-05-23","cited_by_count":1,"area":"moe"},{"id":"2506.07945","title":"ProtocolLLM: RTL Benchmark for SystemVerilog Generation of Communication Protocols","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2508.11925","title":"Optimizing Token Choice for Code Watermarking: An RL Approach","created":"2025-08-16","cited_by_count":1,"area":"safety"},{"id":"2510.13697","title":"On Pretraining for Project-Level Code Completion","created":"2025-10-15","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":"2511.03898","title":"Secure Code Generation at Scale with Reflexion","created":"2025-11-05","cited_by_count":1,"area":null}],"next_cursor":"100"}