{"list":"other","total":54,"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":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"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":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"2503.01307","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","created":"2025-03-03","cited_by_count":377},{"id":"2502.03373","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","created":"2025-02-05","cited_by_count":326},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304},{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209},{"id":"2406.18518","title":"APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets","created":"2024-06-26","cited_by_count":198},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174},{"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":"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},{"id":"2407.20311","title":"Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process","created":"2024-07-29","cited_by_count":108},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104},{"id":"2407.10490","title":"Learning Dynamics of LLM Finetuning","created":"2024-07-15","cited_by_count":95},{"id":"2510.08558","title":"Agent Learning via Early Experience","created":"2025-10-09","cited_by_count":85},{"id":"2510.01179","title":"TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments","created":"2025-10-01","cited_by_count":69},{"id":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54},{"id":"2511.03773","title":"Scaling Agent Learning via Experience Synthesis","created":"2025-11-05","cited_by_count":44},{"id":"2602.21193","title":"On Data Engineering for Scaling LLM Terminal Capabilities","created":"2026-02-24","cited_by_count":43},{"id":"2509.25123","title":"From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones","created":"2025-09-29","cited_by_count":42},{"id":"2602.04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","created":"2026-02-04","cited_by_count":37},{"id":"2602.01244","title":"Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments","created":"2026-02-01","cited_by_count":33},{"id":"2606.23321","title":"Tmax: A simple recipe for terminal agents","created":"2026-06-22","cited_by_count":33},{"id":"2510.15020","title":"The Coverage Principle: How Pre-Training Enables Post-Training","created":"2025-10-16","cited_by_count":30},{"id":"2602.07274","title":"TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents","created":"2026-02-06","cited_by_count":29},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23},{"id":"2602.10999","title":"CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion","created":"2026-02-11","cited_by_count":23},{"id":"2604.25727","title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","created":"2026-04-28","cited_by_count":22},{"id":"2605.20876","title":"Terminal-World: Scaling Terminal-Agent Environments via Agent Skills","created":"2026-05-20","cited_by_count":20},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19},{"id":"2606.29957","title":"SWE-Together: Evaluating Coding Agents in Interactive User Sessions","created":"2026-06-29","cited_by_count":18},{"id":"2505.23604","title":"Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering","created":"2025-05-29","cited_by_count":17},{"id":"2511.13998","title":"LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering","created":"2025-11-17","cited_by_count":16},{"id":"2602.22190","title":"GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL","created":"2026-02-25","cited_by_count":16},{"id":"2604.17596","title":"Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories","created":"2026-04-19","cited_by_count":15},{"id":"2604.04872","title":"Synthetic Sandbox for Training Machine Learning Engineering Agents","created":"2026-04-06","cited_by_count":11},{"id":"2606.24855","title":"OpenThoughts-Agent: Data Recipes for Agentic Models","created":"2026-06-23","cited_by_count":11},{"id":"2605.22535","title":"TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks","created":"2026-05-21","cited_by_count":10},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8},{"id":"2510.06499","title":"Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels","created":"2025-10-07","cited_by_count":8},{"id":"2607.14186","title":"NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs","created":"2026-07-15","cited_by_count":7},{"id":"2603.12698","title":"EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning","created":"2026-03-13","cited_by_count":5},{"id":"2606.18089","title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","created":"2026-06-16","cited_by_count":5},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4},{"id":"2605.14445","title":"FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale","created":"2026-05-14","cited_by_count":3},{"id":"2606.27721","title":"Learning to Reason with Curriculum II: Compositional Generalization","created":"2026-06-26","cited_by_count":3}],"next_cursor":null}