{"total":93,"rows":[{"id":"2510.13786","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","created":"2025-10-15","cited_by_count":101,"area":null},{"id":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95,"area":"agents"},{"id":"2510.08558","title":"Agent Learning via Early Experience","created":"2025-10-09","cited_by_count":85,"area":null},{"id":"2603.00729","title":"Qwen3-Coder-Next Technical Report","created":"2026-02-28","cited_by_count":71,"area":"agents"},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"id":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54,"area":"synth"},{"id":"2602.02482","title":"Expanding the Capabilities of Reinforcement Learning via Text Feedback","created":"2026-02-02","cited_by_count":53,"area":"alignment"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2512.18552","title":"Toward Training Superintelligent Software Agents through Self-Play SWE-RL","created":"2025-12-21","cited_by_count":40,"area":"agents"},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2601.01426","title":"SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving","created":"2026-01-04","cited_by_count":31,"area":null},{"id":"2606.24597","title":"Qwen-AgentWorld: Language World Models for General Agents","created":"2026-06-23","cited_by_count":28,"area":"wm"},{"id":"2602.03419","title":"SWE-World: Building Software Engineering Agents in Docker-Free Environments","created":"2026-02-03","cited_by_count":25,"area":"agents"},{"id":"2602.03411","title":"SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training","created":"2026-02-03","cited_by_count":22,"area":"agents"},{"id":"2606.30616","title":"Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent","created":"2026-06-29","cited_by_count":22,"area":"agents"},{"id":"2601.19834","title":"Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models","created":"2026-01-27","cited_by_count":19,"area":"wm"},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2601.03905","title":"Current Agents Fail to Leverage World Model as Tool for Foresight","created":"2026-01-07","cited_by_count":17,"area":"wm"},{"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":"2604.22748","title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","created":"2026-04-24","cited_by_count":14,"area":"wm"},{"id":"2608.25927","title":"Code World Model: Coding Agent as World Brain","created":"2026-08-26","cited_by_count":14,"area":"wm"},{"id":"2602.01576","title":"Generative Visual Code Mobile World Models","created":"2026-02-02","cited_by_count":13,"area":"wm"},{"id":"2601.22129","title":"SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents","created":"2026-01-29","cited_by_count":12,"area":"lr"},{"id":"2512.24618","title":"Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models","created":"2025-12-31","cited_by_count":10,"area":"agents"},{"id":"2601.05930","title":"Can We Predict Before Executing Machine Learning Agents?","created":"2026-01-09","cited_by_count":10,"area":"agents"},{"id":"2601.20789","title":"SERA: Soft-Verified Efficient Repository Agents","created":"2026-01-28","cited_by_count":10,"area":"agents"},{"id":"2608.13940","title":"AI Research Preference Models","created":"2026-08-14","cited_by_count":10,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2605.30880","title":"PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments","created":"2026-05-29","cited_by_count":7,"area":"wm"},{"id":"2510.03415","title":"LLMs Lean on Priors, Not Programming Language Semantics","created":"2025-10-03","cited_by_count":6,"area":"lr"},{"id":"2512.13874","title":"SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning","created":"2025-12-15","cited_by_count":6,"area":null},{"id":"2512.21577","title":"A Unified Definition of Hallucination: It's The World Model, Stupid!","created":"2025-12-25","cited_by_count":6,"area":"wm"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2602.14814","title":"Learning State-Tracking from Code Using Linear RNNs","created":"2026-02-16","cited_by_count":6,"area":null},{"id":"2604.01496","title":"From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents","created":"2026-04-02","cited_by_count":6,"area":"agents"},{"id":"2512.23236","title":"KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta","created":"2025-12-29","cited_by_count":5,"area":"agents"},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2601.13247","title":"Aligning Agentic World Models via Knowledgeable Experience Learning","created":"2026-01-19","cited_by_count":5,"area":"wm"},{"id":"2602.06130","title":"Self-Improving World Modelling with Latent Actions","created":"2026-02-05","cited_by_count":5,"area":"wm"},{"id":"2602.07672","title":"Debugging code world models","created":"2026-02-07","cited_by_count":5,"area":"wm"},{"id":"2603.25681","title":"Self-Improvement of Large Language Models: A Technical Overview and Future Outlook","created":"2026-03-26","cited_by_count":5,"area":"synth"},{"id":"2605.15871","title":"Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design","created":"2026-05-15","cited_by_count":5,"area":"agents"},{"id":"2602.22124","title":"SWE-Prot\\'eg\\'e: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents","created":"2026-02-25","cited_by_count":4,"area":"agents"},{"id":"2604.03144","title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2607.24112","title":"Scaling GUI Agents with Visual State Transitions","created":"2026-07-27","cited_by_count":4,"area":"agents"},{"id":"2511.21638","title":"Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF","created":"2025-11-26","cited_by_count":3,"area":"lr"},{"id":"2512.14917","title":"Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings","created":"2025-12-16","cited_by_count":3,"area":"lr"},{"id":"2601.22530","title":"Enhancing Table Reasoning with Deterministic Table-State Rewards","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2603.24202","title":"A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula","created":"2026-03-25","cited_by_count":3,"area":"synth"},{"id":"2604.03253","title":"Self-Execution Simulation Improves Coding Models","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2604.04707","title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","created":"2026-04-06","cited_by_count":3,"area":"wm"},{"id":"2604.11419","title":"Beyond RAG for Cyber Threat Intelligence: A Systematic Evaluation of Graph-Based and Agentic Retrieval","created":"2026-04-13","cited_by_count":3,"area":"agents"},{"id":"2601.18987","title":"LLMs versus the Halting Problem: Characterizing Program Termination Reasoning","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2605.12178","title":"Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics","created":"2026-05-12","cited_by_count":2,"area":"wm"},{"id":"2605.17453","title":"Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2605.28751","title":"Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2607.27146","title":"MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2602.00785","title":"World Models as an Intermediary between Agents and the Real World","created":"2026-01-31","cited_by_count":1,"area":"wm"},{"id":"2603.07927","title":"SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2604.28181","title":"Synthetic Computers at Scale for Long-Horizon Productivity Simulation","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.17958","title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2607.05188","title":"Latent Programming Horizons in Coding Agents","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2609.00455","title":"Towards a Belief-Based World Model for LLM Agents","created":"2026-08-31","cited_by_count":1,"area":"wm"},{"id":"2609.09163","title":"World-Time Compute with Verified Code World Models","created":"2026-07-07","cited_by_count":1,"area":"wm"},{"id":"2603.00601","title":"Theory of Code Space: Do Code Agents Understand Software Architecture?","created":"2026-02-28","cited_by_count":0,"area":"agents"},{"id":"2603.13640","title":"SemRep: Generative Code Representation Learning with Code Transformations","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.20926","title":"Learning Reasoning World Models for Parallel Code","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2604.22601","title":"From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.06184","title":"Teaching LLMs Program Semantics via Symbolic Execution Traces","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.00472","title":"CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action space","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.07527","title":"Post-training is (Massive) Supervised Learning","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.17508","title":"When the Next Step Is Not One Step: Distribution-Aware Execution Modeling for Concurrent Go Programs","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.21974","title":"Fine-Tuning Large Language Models for Quantum Reasoning","created":"2026-06-20","cited_by_count":0,"area":"lr"},{"id":"2606.23690","title":"Beyond the Autoregressive Horizon: A Comprehensive Survey of Diffusion Models, World Modelling, and State Space Models for Code","created":"2026-04-09","cited_by_count":0,"area":"wm"},{"id":"2606.26660","title":"Generating Special Triangulations with Transformers","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.27406","title":"Towards Evaluation of Implicit Software World Models in Coding LLMs","created":"2026-06-25","cited_by_count":0,"area":"wm"},{"id":"2607.01490","title":"Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2607.21677","title":"Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.25970","title":"Reinforcement Learning for Code Optimization","created":"2026-07-28","cited_by_count":0,"area":"alignment"},{"id":"2608.02713","title":"Quo Vadis, World Modeling?","created":"2026-08-03","cited_by_count":0,"area":"wm"},{"id":"2609.01067","title":"World Model-Guided Reinforcement Learning via Counterfactual User Engagement Simulation","created":"2026-09-01","cited_by_count":0,"area":"wm"},{"id":"2609.01608","title":"WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling","created":"2026-06-02","cited_by_count":0,"area":"wm"},{"id":"2609.19551","title":"Continual Enterprise World Model Discovery in Dynamic Systems","created":"2026-09-17","cited_by_count":0,"area":"wm"},{"id":"2609.28416","title":"Agent-Editing World Model: Rethinking World Modeling for LLM Agents","created":"2026-09-23","cited_by_count":0,"area":"wm"},{"id":"2609.36371","title":"LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.01215","title":"AutoGUIWorld: Image Generators as Visual World Models for GUI Agent","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.04737","title":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.04940","title":"Software World Models: From Consequence Prediction to Decision Value","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.11889","title":"Evaluating Exact Output and Checkpoint-State Prediction in Real Programs","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12598","title":"Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.15368","title":"ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs","created":"2026-10-11","cited_by_count":0,"area":"wm"}],"next_cursor":null}