{"total":57,"rows":[{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263,"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":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151,"area":"lr"},{"id":"2506.18824","title":"Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories","created":"2025-06-23","cited_by_count":81,"area":"lr"},{"id":"2508.02085","title":"SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents","created":"2025-08-04","cited_by_count":69,"area":"lr"},{"id":"2504.07986","title":"SEAL: Steerable Reasoning Calibration of Large Language Models for Free","created":"2025-04-07","cited_by_count":68,"area":"lr"},{"id":"2601.02163","title":"EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning","created":"2026-01-05","cited_by_count":54,"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":"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":"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":"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":"2504.00810","title":"Z1: Efficient Test-time Scaling with Code","created":"2025-04-01","cited_by_count":35,"area":"lr"},{"id":"2502.12468","title":"MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation","created":"2025-02-18","cited_by_count":32,"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":"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":"2410.03524","title":"Steering Large Language Models between Code Execution and Textual Reasoning","created":"2024-10-04","cited_by_count":24,"area":"lr"},{"id":"2507.05269","title":"CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks","created":"2025-07-03","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":"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":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"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":"2509.15738","title":"GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning","created":"2025-09-19","cited_by_count":13,"area":"lr"},{"id":"2509.17336","title":"Mano Technical Report","created":"2025-09-22","cited_by_count":13,"area":"lr"},{"id":"2503.00912","title":"HiBench: Benchmarking LLMs Capability on Hierarchical Structure Reasoning","created":"2025-03-02","cited_by_count":12,"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":"2505.13652","title":"Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents","created":"2025-05-19","cited_by_count":10,"area":"lr"},{"id":"2606.02373","title":"Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses","created":"2026-06-01","cited_by_count":10,"area":"lr"},{"id":"2603.17829","title":"CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents","created":"2026-03-18","cited_by_count":9,"area":"lr"},{"id":"2505.16785","title":"CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language Models","created":"2025-05-22","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":"2601.03093","title":"ATLAS: Verifier-Guided Adaptive Latent Activation Steering for Efficient LLM Reasoning","created":"2026-01-06","cited_by_count":6,"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":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","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":"2603.01896","title":"Agentic Code Reasoning","created":"2026-03-02","cited_by_count":4,"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":"2604.26102","title":"SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent","created":"2026-04-28","cited_by_count":3,"area":"lr"},{"id":"2607.13439","title":"DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection","created":"2026-07-15","cited_by_count":3,"area":"lr"},{"id":"2509.07159","title":"PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning","created":"2025-09-08","cited_by_count":2,"area":"lr"},{"id":"2602.05242","title":"EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering","created":"2026-02-05","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":"2605.29277","title":"Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QA","created":"2026-05-28","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":"2510.16059","title":"SIADAFIX: issue description response for adaptive program repair","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2602.05385","title":"IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models","created":"2026-02-05","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":"2603.19138","title":"Implicit Patterns in LLM-Based Binary Analysis","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2604.12881","title":"Evaluating LLMs Code Reasoning Under Real-World Context","created":"2026-04-14","cited_by_count":0,"area":"lr"},{"id":"2609.23808","title":"FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model","created":"2026-09-20","cited_by_count":0,"area":"lr"},{"id":"2610.18755","title":"PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}