{"list":"other","total":76,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912},{"id":"2406.07524","title":"Simple and Effective Masked Diffusion Language Models","created":"2024-06-11","cited_by_count":848},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"2406.04329","title":"Simplified and Generalized Masked Diffusion for Discrete Data","created":"2024-06-06","cited_by_count":626},{"id":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468},{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417},{"id":"2503.09573","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","created":"2025-03-12","cited_by_count":409},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407},{"id":"2406.03736","title":"Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data","created":"2024-06-06","cited_by_count":381},{"id":"2408.05517","title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","created":"2024-08-10","cited_by_count":355},{"id":"2408.14837","title":"Diffusion Models Are Real-Time Game Engines","created":"2024-08-27","cited_by_count":296},{"id":"2506.14245","title":"Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs","created":"2025-06-17","cited_by_count":289},{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281},{"id":"2410.17891","title":"Scaling Diffusion Language Models via Adaptation from Autoregressive Models","created":"2024-10-23","cited_by_count":274},{"id":"2405.00451","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","created":"2024-05-01","cited_by_count":241},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205},{"id":"2410.18514","title":"Scaling up Masked Diffusion Models on Text","created":"2024-10-24","cited_by_count":199},{"id":"2506.20639","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","created":"2025-06-25","cited_by_count":187},{"id":"2504.03601","title":"APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay","created":"2025-04-04","cited_by_count":167},{"id":"2512.15745","title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B","created":"2025-12-10","cited_by_count":166},{"id":"2509.02479","title":"SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning","created":"2025-09-02","cited_by_count":146},{"id":"2510.06303","title":"SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation","created":"2025-10-07","cited_by_count":129},{"id":"2508.00083","title":"A Survey on Code Generation with LLM-based Agents","created":"2025-07-31","cited_by_count":106},{"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},{"id":"2407.03502","title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","created":"2024-07-03","cited_by_count":89},{"id":"2510.25726","title":"The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution","created":"2025-10-29","cited_by_count":85},{"id":"2506.14965","title":"Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective","created":"2025-06-17","cited_by_count":76},{"id":"2602.10090","title":"Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning","created":"2026-02-10","cited_by_count":66},{"id":"2601.05808","title":"EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis","created":"2026-01-09","cited_by_count":63},{"id":"1904.03971","title":"Jointly Measuring Diversity and Quality in Text Generation Models","created":"2019-04-08","cited_by_count":61},{"id":"2503.14023","title":"Synthetic Data Generation Using Large Language Models: Advances in Text and Code","created":"2025-03-18","cited_by_count":61},{"id":"2602.08676","title":"LLaDA2.1: Speeding Up Text Diffusion via Token Editing","created":"2026-02-09","cited_by_count":54},{"id":"2601.20975","title":"DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents","created":"2026-01-28","cited_by_count":50},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49},{"id":"2504.04736","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","created":"2025-04-07","cited_by_count":45},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","cited_by_count":44},{"id":"2511.03773","title":"Scaling Agent Learning via Experience Synthesis","created":"2025-11-05","cited_by_count":44},{"id":"2506.11425","title":"Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards","created":"2025-06-13","cited_by_count":42},{"id":"2512.18832","title":"From Word to World: Can Large Language Models be Implicit Text-based World Models?","created":"2025-12-21","cited_by_count":42},{"id":"2512.22737","title":"WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference","created":"2025-12-28","cited_by_count":41},{"id":"2403.01081","title":"LAB: Large-Scale Alignment for ChatBots","created":"2024-03-02","cited_by_count":39},{"id":"2511.23404","title":"LFM2 Technical Report","created":"2025-11-28","cited_by_count":37},{"id":"2603.20278","title":"OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis","created":"2026-03-17","cited_by_count":37},{"id":"2512.14067","title":"Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed","created":"2025-12-16","cited_by_count":33},{"id":"2409.08239","title":"Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources","created":"2024-09-12","cited_by_count":28},{"id":"2604.15149","title":"LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking","created":"2026-04-16","cited_by_count":28},{"id":"2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","created":"2025-10-01","cited_by_count":26},{"id":"2501.12766","title":"NExtLong: Toward Effective Long-Context Training without Long Documents","created":"2025-01-22","cited_by_count":20},{"id":"2510.14969","title":"LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training","created":"2025-10-16","cited_by_count":18},{"id":"2411.01775","title":"Eurekaverse: Environment Curriculum Generation via Large Language Models","created":"2024-11-04","cited_by_count":16},{"id":"2511.07338","title":"DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas","created":"2025-11-10","cited_by_count":15},{"id":"2601.22511","title":"Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards","created":"2026-01-30","cited_by_count":10},{"id":"2502.16684","title":"WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale","created":"2025-02-23","cited_by_count":9},{"id":"2604.10866","title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","created":"2026-04-13","cited_by_count":7},{"id":"2510.20668","title":"From Masks to Worlds: A Hitchhiker's Guide to World Models","created":"2025-10-23","cited_by_count":5},{"id":"2602.20117","title":"ReSyn: Autonomously Scaling Synthetic Environments for Reasoning Models","created":"2026-02-23","cited_by_count":5},{"id":"2504.12637","title":"Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation","created":"2025-04-17","cited_by_count":4},{"id":"2603.12011","title":"Can RL Improve Generalization of LLM Agents? An Empirical Study","created":"2026-03-12","cited_by_count":4},{"id":"2508.09193","title":"Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL","created":"2025-08-08","cited_by_count":3},{"id":"2509.21234","title":"AbideGym: Turning Static RL Worlds into Adaptive Challenges","created":"2025-09-25","cited_by_count":1},{"id":"2603.22075","title":"Autoregressive vs. Masked Diffusion Language Models: A Controlled Comparison","created":"2026-03-23","cited_by_count":1}],"next_cursor":null}