{"total":134,"rows":[{"id":"2509.25140","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","created":"2025-09-29","cited_by_count":284,"area":"lr"},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263,"area":"lr"},{"id":"2509.02544","title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","created":"2025-09-02","cited_by_count":215,"area":"lr"},{"id":"2505.16421","title":"WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning","created":"2025-05-22","cited_by_count":165,"area":"lr"},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"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":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"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":"2511.20639","title":"Latent Collaboration in Multi-Agent Systems","created":"2025-11-25","cited_by_count":73,"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":"2410.02052","title":"ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning","created":"2024-10-02","cited_by_count":62,"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":"2511.17006","title":"Budget-Aware Tool Use Enables Effective Agent Scaling","created":"2025-11-21","cited_by_count":44,"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":"2410.04047","title":"TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis","created":"2024-10-05","cited_by_count":29,"area":"lr"},{"id":"2504.09772","title":"Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning","created":"2025-04-14","cited_by_count":29,"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":"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":"2506.04405","title":"MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science","created":"2025-06-04","cited_by_count":23,"area":"lr"},{"id":"2504.06260","title":"FEABench: Evaluating Language Models on Multiphysics Reasoning Ability","created":"2025-04-08","cited_by_count":22,"area":"lr"},{"id":"2407.10718","title":"Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning","created":"2024-07-15","cited_by_count":18,"area":"lr"},{"id":"2503.04479","title":"ToolFuzz -- Automated Agent Tool Testing","created":"2025-03-06","cited_by_count":18,"area":"lr"},{"id":"2510.02230","title":"The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models","created":"2025-10-02","cited_by_count":18,"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":"2604.14820","title":"SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling","created":"2026-04-16","cited_by_count":16,"area":"lr"},{"id":"2508.03012","title":"Tool-integrated Reinforcement Learning for Repo Deep Search","created":"2025-08-05","cited_by_count":15,"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":"2511.04898","title":"Real-Time Reasoning Agents in Evolving Environments","created":"2025-11-07","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":"2512.02624","title":"PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design Understanding","created":"2025-12-02","cited_by_count":14,"area":"lr"},{"id":"2601.01678","title":"HeurekaBench: A Benchmarking Framework for AI Co-scientist","created":"2026-01-04","cited_by_count":12,"area":"lr"},{"id":"2603.04304","title":"$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners","created":"2026-03-04","cited_by_count":12,"area":"lr"},{"id":"2607.14171","title":"Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning","created":"2026-07-15","cited_by_count":12,"area":"lr"},{"id":"2603.12634","title":"Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents","created":"2026-03-13","cited_by_count":11,"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":"2602.13103","title":"R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training","created":"2026-02-13","cited_by_count":10,"area":"lr"},{"id":"2606.10662","title":"Decentralized Multi-Agent Systems with Shared Context","created":"2026-06-09","cited_by_count":10,"area":"lr"},{"id":"2508.19827","title":"Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?","created":"2025-08-27","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":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2606.03854","title":"CLI-Anything: Towards Agent-Native Computer Use","created":"2026-06-02","cited_by_count":9,"area":"lr"},{"id":"2506.15695","title":"SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models","created":"2025-05-28","cited_by_count":8,"area":"lr"},{"id":"2510.09577","title":"Dyna-Mind: Learning to Simulate from Experience for Better AI Agents","created":"2025-10-10","cited_by_count":8,"area":"lr"},{"id":"2603.07379","title":"SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions","created":"2026-03-07","cited_by_count":8,"area":"lr"},{"id":"2603.21972","title":"Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2408.11326","title":"Automating Thought of Search: A Journey Towards Soundness and Completeness","created":"2024-08-21","cited_by_count":7,"area":"lr"},{"id":"2512.23631","title":"BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2503.10042","title":"EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability","created":"2025-03-13","cited_by_count":6,"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":"2602.01566","title":"FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents","created":"2026-02-02","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":"2605.11633","title":"Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations","created":"2026-05-12","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":"2605.30314","title":"SpecBench: Evaluating Specification-Level Reasoning for Software Engineering LLM Agents","created":"2026-05-28","cited_by_count":6,"area":"lr"},{"id":"2506.00172","title":"Breakpoint: Scalable evaluation of system-level reasoning in LLM code agents","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2510.10047","title":"SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning","created":"2025-10-11","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":"2602.11210","title":"SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents","created":"2026-02-11","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":"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":"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":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","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":"2504.03635","title":"Finding the Minimal Parameter Budget for Implicit Reasoning: A Data Complexity Driven Scaling Law for Language Models","created":"2025-04-04","cited_by_count":3,"area":"lr"},{"id":"2510.22087","title":"QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture","created":"2025-10-24","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":"2605.12460","title":"Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2606.10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","created":"2026-06-09","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":"2506.05278","title":"Micro-Act: Mitigating Knowledge Conflict in LLM-based RAG via Actionable Self-Reasoning","created":"2025-06-05","cited_by_count":2,"area":"lr"},{"id":"2511.00488","title":"\\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs","created":"2025-11-01","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":"2604.00824","title":"Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs","created":"2026-04-01","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":"2604.18364","title":"Training and Agentic Inference Strategies for LLM-based Manim Animation Generation","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2605.14163","title":"Agentic Systems as Boosting Weak Reasoning Models","created":"2026-05-13","cited_by_count":2,"area":"lr"},{"id":"2605.15315","title":"Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning","created":"2026-05-14","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":"2606.10694","title":"REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs","created":"2026-06-09","cited_by_count":2,"area":"lr"},{"id":"2606.22798","title":"Does the Same Token Mean the Same State? MoE Routing as Signal for Reasoning Control","created":"2026-06-22","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":"2607.27703","title":"SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them","created":"2026-07-30","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":"2507.05065","title":"Replacing thinking with tool usage enables reasoning in small language models","created":"2025-07-07","cited_by_count":1,"area":"lr"},{"id":"2510.03349","title":"AgentCaster: Reasoning-Guided Tornado Forecasting","created":"2025-10-02","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":"2601.10649","title":"MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning","created":"2026-01-15","cited_by_count":1,"area":"lr"},{"id":"2602.16069","title":"The Limits of Long-Context Reasoning in Automated Bug Fixing","created":"2026-02-17","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}