{"total":263,"rows":[{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275,"area":"lr"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2504.07164","title":"R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents","created":"2025-04-09","cited_by_count":158,"area":"lr"},{"id":"2505.23885","title":"OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation","created":"2025-05-29","cited_by_count":131,"area":"lr"},{"id":"2505.14970","title":"Self-Evolving Curriculum for LLM Reasoning","created":"2025-05-20","cited_by_count":112,"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":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"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":"2510.02387","title":"CWM: An Open-Weights LLM for Research on Code Generation with World Models","created":"2025-09-30","cited_by_count":93,"area":"wm"},{"id":"2603.22435","title":"CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation","created":"2026-03-23","cited_by_count":88,"area":"vla"},{"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":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2606.30406","title":"MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training","created":"2026-06-29","cited_by_count":72,"area":"distill"},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"area":null},{"id":"2507.14111","title":"CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning","created":"2025-07-18","cited_by_count":61,"area":"lr"},{"id":"2503.23157","title":"Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL","created":"2025-03-29","cited_by_count":59,"area":"lr"},{"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":"2504.15275","title":"Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning","created":"2025-04-21","cited_by_count":50,"area":"lr"},{"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":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"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":"2509.19199","title":"Agentic Reinforcement Learning with Implicit Step Rewards","created":"2025-09-23","cited_by_count":47,"area":"agents"},{"id":"2509.09265","title":"Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents","created":"2025-09-11","cited_by_count":46,"area":"agents"},{"id":"2505.14668","title":"ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions","created":"2025-05-20","cited_by_count":45,"area":"agents"},{"id":"2512.22087","title":"Context as a Tool: Context Management for Long-Horizon SWE-Agents","created":"2025-12-26","cited_by_count":43,"area":"agents"},{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2506.11425","title":"Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards","created":"2025-06-13","cited_by_count":42,"area":"lr"},{"id":"2509.06216","title":"Agentic Software Engineering: Foundational Pillars and a Research Roadmap","created":"2025-09-07","cited_by_count":41,"area":"agents"},{"id":"2509.23045","title":"Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents","created":"2025-09-27","cited_by_count":41,"area":"agents"},{"id":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2504.00810","title":"Z1: Efficient Test-time Scaling with Code","created":"2025-04-01","cited_by_count":35,"area":"lr"},{"id":"2509.19128","title":"PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation","created":"2025-09-23","cited_by_count":32,"area":"lr"},{"id":"2510.05094","title":"VChain: Chain-of-Visual-Thought for Reasoning in Video Generation","created":"2025-10-06","cited_by_count":32,"area":null},{"id":"2503.12759","title":"RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning","created":"2025-03-17","cited_by_count":30,"area":"rag"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2510.19898","title":"BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills","created":"2025-10-22","cited_by_count":30,"area":null},{"id":"2512.24873","title":"Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem","created":"2025-12-31","cited_by_count":30,"area":"agents"},{"id":"2503.19618","title":"Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data","created":"2025-03-25","cited_by_count":29,"area":null},{"id":"2509.23863","title":"SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models","created":"2025-09-28","cited_by_count":29,"area":"lr"},{"id":"2512.21919","title":"SWE-RM: Execution-free Feedback For Software Engineering Agents","created":"2025-12-26","cited_by_count":28,"area":"lr"},{"id":"2503.23803","title":"Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute","created":"2025-03-31","cited_by_count":26,"area":"lr"},{"id":"2601.04171","title":"Agentic Rubrics as Contextual Verifiers for SWE Agents","created":"2026-01-07","cited_by_count":25,"area":"lr"},{"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":"2508.03905","title":"Sotopia-RL: Reward Design for Social Intelligence","created":"2025-08-05","cited_by_count":24,"area":"alignment"},{"id":"2503.21961","title":"Entropy-Gated Branching for Efficient Test-Time Reasoning","created":"2025-03-27","cited_by_count":22,"area":"lr"},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2508.00910","title":"Cyber-Zero: Training Cybersecurity Agents without Runtime","created":"2025-07-29","cited_by_count":22,"area":"agents"},{"id":"2512.03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","created":"2025-12-02","cited_by_count":22,"area":"agents"},{"id":"2602.09892","title":"Immersion in the GitHub Universe: Scaling Coding Agents to Mastery","created":"2026-02-10","cited_by_count":22,"area":"agents"},{"id":"2603.03194","title":"BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?","created":"2026-03-03","cited_by_count":22,"area":"agents"},{"id":"2505.14625","title":"TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2506.10974","title":"AutoMind: Adaptive Knowledgeable Agent for Automated Data Science","created":"2025-06-12","cited_by_count":20,"area":"agents"},{"id":"2509.22638","title":"Language Models Can Learn from Verbal Feedback Without Scalar Rewards","created":"2025-09-26","cited_by_count":18,"area":null},{"id":"2505.23604","title":"Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering","created":"2025-05-29","cited_by_count":17,"area":"lr"},{"id":"2509.09853","title":"SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints","created":"2025-09-11","cited_by_count":17,"area":"agents"},{"id":"2509.11963","title":"ToolRM: Outcome Reward Models for Tool-Calling Large Language Models","created":"2025-09-15","cited_by_count":17,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16,"area":null},{"id":"2506.08311","title":"Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study","created":"2025-06-10","cited_by_count":16,"area":"agents"},{"id":"2510.15414","title":"MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs","created":"2025-10-17","cited_by_count":16,"area":"lr"},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"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":"2505.21668","title":"R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning","created":"2025-05-27","cited_by_count":15,"area":"lr"},{"id":"2508.18370","title":"Training Language Model Agents to Find Vulnerabilities with CTF-Dojo","created":"2025-08-25","cited_by_count":15,"area":"agents"},{"id":"2510.01279","title":"TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture","created":"2025-09-30","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":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2606.28434","title":"SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents","created":"2026-06-26","cited_by_count":15,"area":"agents"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2509.01684","title":"Reinforcement Learning for Machine Learning Engineering Agents","created":"2025-09-01","cited_by_count":14,"area":"lr"},{"id":"2602.12268","title":"CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use","created":"2026-02-12","cited_by_count":14,"area":"agents"},{"id":"2511.14846","title":"Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization","created":"2025-11-18","cited_by_count":13,"area":"lr"},{"id":"2505.18955","title":"Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Models","created":"2025-05-25","cited_by_count":12,"area":"lr"},{"id":"2505.20196","title":"Temporal Sampling for Forgotten Reasoning in LLMs","created":"2025-05-26","cited_by_count":12,"area":"lr"},{"id":"2506.16136","title":"Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing","created":"2025-06-19","cited_by_count":12,"area":"lr"},{"id":"2508.10118","title":"From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation","created":"2025-08-13","cited_by_count":12,"area":"lr"},{"id":"2605.22781","title":"DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback","created":"2026-05-21","cited_by_count":12,"area":"agents"},{"id":"2607.14171","title":"Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning","created":"2026-07-15","cited_by_count":12,"area":"lr"},{"id":"2510.25992","title":"Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning","created":"2025-10-29","cited_by_count":11,"area":"lr"},{"id":"2512.10398","title":"Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases","created":"2025-12-11","cited_by_count":11,"area":"agents"},{"id":"2601.13572","title":"Behavior Knowledge Merge in Reinforced Agentic Models","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"id":"2601.16206","title":"Computer Environments Elicit General Agentic Intelligence in LLMs","created":"2026-01-22","cited_by_count":11,"area":"agents"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2508.13023","title":"G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2512.00908","title":"Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs","created":"2025-11-30","cited_by_count":10,"area":"lr"},{"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":"2604.17931","title":"LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent","created":"2026-04-20","cited_by_count":10,"area":"agents"},{"id":"2505.20561","title":"Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning","created":"2025-05-26","cited_by_count":9,"area":"lr"},{"id":"2505.20777","title":"TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs","created":"2025-05-27","cited_by_count":9,"area":"lr"},{"id":"2509.24771","title":"LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space","created":"2025-09-29","cited_by_count":9,"area":"lr"},{"id":"2602.04634","title":"WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning","created":"2026-02-04","cited_by_count":9,"area":"agents"},{"id":"2602.23647","title":"SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair","created":"2026-02-27","cited_by_count":9,"area":"agents"},{"id":"2606.07412","title":"Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills","created":"2026-06-05","cited_by_count":9,"area":"agents"},{"id":"2607.22724","title":"Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-07-22","cited_by_count":9,"area":"agents"}],"next_cursor":"100"}