{"total":81,"rows":[{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467,"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":"2502.08235","title":"The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks","created":"2025-02-12","cited_by_count":152,"area":"lr"},{"id":"2505.20286","title":"Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution","created":"2025-05-26","cited_by_count":116,"area":"lr"},{"id":"2503.01491","title":"What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret","created":"2025-03-03","cited_by_count":98,"area":"lr"},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96,"area":"lr"},{"id":"2507.23370","title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","created":"2025-07-31","cited_by_count":94,"area":"lr"},{"id":"2511.16043","title":"Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning","created":"2025-11-20","cited_by_count":75,"area":"lr"},{"id":"2507.23348","title":"SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution","created":"2025-07-31","cited_by_count":53,"area":"lr"},{"id":"2508.14040","title":"ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents","created":"2025-08-19","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":"2506.12286","title":"The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason","created":"2025-06-14","cited_by_count":49,"area":"lr"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"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":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"id":"2508.03501","title":"Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":36,"area":"lr"},{"id":"2503.07832","title":"RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code","created":"2025-03-10","cited_by_count":30,"area":"lr"},{"id":"2502.20127","title":"SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning","created":"2025-02-27","cited_by_count":28,"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":"2601.04171","title":"Agentic Rubrics as Contextual Verifiers for SWE Agents","created":"2026-01-07","cited_by_count":25,"area":"lr"},{"id":"2410.03524","title":"Steering Large Language Models between Code Execution and Textual Reasoning","created":"2024-10-04","cited_by_count":24,"area":"lr"},{"id":"2601.11100","title":"ReCreate: Reasoning and Creating Domain Agents Driven by Experience","created":"2026-01-16","cited_by_count":24,"area":"lr"},{"id":"2410.09302","title":"Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization","created":"2024-10-11","cited_by_count":22,"area":"lr"},{"id":"2604.11753","title":"Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks","created":"2026-04-13","cited_by_count":18,"area":"lr"},{"id":"2509.22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2509.01684","title":"Reinforcement Learning for Machine Learning Engineering Agents","created":"2025-09-01","cited_by_count":14,"area":"lr"},{"id":"2602.07900","title":"Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents","created":"2026-02-08","cited_by_count":14,"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":"2601.22129","title":"SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents","created":"2026-01-29","cited_by_count":12,"area":"lr"},{"id":"2411.03455","title":"Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents","created":"2024-11-05","cited_by_count":8,"area":"lr"},{"id":"2503.23314","title":"SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science","created":"2025-03-30","cited_by_count":7,"area":"lr"},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2604.10291","title":"TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale","created":"2026-04-11","cited_by_count":6,"area":"lr"},{"id":"2604.26275","title":"Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering","created":"2026-04-29","cited_by_count":6,"area":"lr"},{"id":"2605.05980","title":"TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering","created":"2026-05-07","cited_by_count":6,"area":"lr"},{"id":"2605.28732","title":"MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems","created":"2026-05-27","cited_by_count":6,"area":"lr"},{"id":"2510.22775","title":"Scalable Supervision for Software Agents via Patch Reasoning","created":"2025-10-26","cited_by_count":5,"area":"lr"},{"id":"2601.18044","title":"RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Models","created":"2026-01-25","cited_by_count":5,"area":"lr"},{"id":"2603.03655","title":"Mozi: Governed Autonomy for Drug Discovery LLM Agents","created":"2026-03-04","cited_by_count":5,"area":"lr"},{"id":"2605.11556","title":"Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers","created":"2026-05-12","cited_by_count":5,"area":"lr"},{"id":"2508.02121","title":"A Survey on AgentOps: Categorization, Challenges, and Future Directions","created":"2025-08-04","cited_by_count":4,"area":"lr"},{"id":"2510.20909","title":"Code-enabled language models can outperform reasoning models on diverse tasks","created":"2025-10-23","cited_by_count":4,"area":"lr"},{"id":"2511.00066","title":"Sharpness-Guided Group Relative Policy Optimization via Probability Shaping","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2512.01822","title":"InnoGym: Benchmarking the Innovation Potential of AI Agents","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2512.22469","title":"GraphLocator: Graph-guided Causal Reasoning for Issue Localization","created":"2025-12-27","cited_by_count":4,"area":"lr"},{"id":"2603.01692","title":"Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2605.15224","title":"ICRL: Learning to Internalize Self-Critique with Reinforcement Learning","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2608.17393","title":"LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents","created":"2026-08-18","cited_by_count":4,"area":"lr"},{"id":"2507.05707","title":"Agentic-R1: Distilled Dual-Strategy Reasoning","created":"2025-07-08","cited_by_count":3,"area":"lr"},{"id":"2510.07761","title":"Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers","created":"2025-10-09","cited_by_count":3,"area":"lr"},{"id":"2601.23257","title":"From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2602.13574","title":"Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation","created":"2026-02-14","cited_by_count":3,"area":"lr"},{"id":"2604.15075","title":"Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2604.26102","title":"SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent","created":"2026-04-28","cited_by_count":3,"area":"lr"},{"id":"2607.27267","title":"FAVA: Formal Authorization for Verified Agents with Evidence-Backed Permission Graphs","created":"2026-07-29","cited_by_count":3,"area":"lr"},{"id":"2512.19799","title":"PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research","created":"2025-12-22","cited_by_count":2,"area":"lr"},{"id":"2602.06090","title":"SVRepair: Structured Visual Reasoning for Automated Program Repair","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2604.11045","title":"Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure","created":"2026-04-13","cited_by_count":2,"area":"lr"},{"id":"2607.02436","title":"Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study","created":"2026-07-02","cited_by_count":2,"area":"lr"},{"id":"2607.18859","title":"PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2608.16742","title":"TDD-Agent: Test-Driven Reasoning for Code Generation","created":"2026-08-17","cited_by_count":2,"area":"lr"},{"id":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2609.04518","title":"Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence","created":"2026-09-03","cited_by_count":2,"area":"lr"},{"id":"2508.02841","title":"A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answering","created":"2025-08-04","cited_by_count":1,"area":"lr"},{"id":"2510.16059","title":"SIADAFIX: issue description response for adaptive program repair","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2604.03242","title":"DRAFT: Task Decoupled Latent Reasoning for Agent Safety","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"id":"2604.09608","title":"Unifying Ontology Construction and Semantic Alignment for Deterministic Enterprise Reasoning at Scale","created":"2026-03-11","cited_by_count":1,"area":"lr"},{"id":"2604.16469","title":"B-PASTE: Beam-Aware Pattern-Guided Speculative Execution for Resource-Constrained LLM Agents","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2607.03065","title":"Spectral Rewiring for Exploration, Purification, and Model Merging","created":"2026-07-03","cited_by_count":1,"area":"lr"},{"id":"2601.21469","title":"Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.19407","title":"Multi-CoLoR: Context-Aware Localization and Reasoning across Multi-Language Codebases","created":"2026-02-23","cited_by_count":0,"area":"lr"},{"id":"2604.12102","title":"Spatial Atlas: Compute-Grounded Reasoning for Spatial-Aware Research Agent Benchmarks","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2604.20926","title":"Learning Reasoning World Models for Parallel Code","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2605.07276","title":"Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.12746","title":"CoT-Guard: Small Models for Strong Monitoring","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2606.07689","title":"Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2609.23377","title":"One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents","created":"2026-09-20","cited_by_count":0,"area":"lr"},{"id":"2609.39740","title":"LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillation","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.05241","title":"StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}