{"total":38,"rows":[{"id":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214,"area":"lr"},{"id":"2506.18959","title":"From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents","created":"2025-06-23","cited_by_count":51,"area":"lr"},{"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":"2505.24714","title":"FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation","created":"2025-05-30","cited_by_count":30,"area":"lr"},{"id":"2509.11035","title":"Free-MAD: Consensus-Free Multi-Agent Debate","created":"2025-09-14","cited_by_count":29,"area":"lr"},{"id":"2508.17692","title":"LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios","created":"2025-08-25","cited_by_count":26,"area":"lr"},{"id":"2602.18998","title":"Benchmark Test-Time Scaling of General LLM Agents","created":"2026-02-22","cited_by_count":26,"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":"2511.13288","title":"Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO","created":"2025-11-17","cited_by_count":18,"area":"lr"},{"id":"2510.21557","title":"Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts","created":"2025-10-24","cited_by_count":13,"area":"lr"},{"id":"2506.21924","title":"SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding","created":"2025-06-27","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":"2603.02795","title":"VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning","created":"2026-03-03","cited_by_count":9,"area":"lr"},{"id":"2505.19952","title":"Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2603.01761","title":"Position: Modular Memory is the Key to Continual Learning Agents","created":"2026-03-02","cited_by_count":8,"area":"lr"},{"id":"2510.11184","title":"Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2508.03178","title":"Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following","created":"2025-08-05","cited_by_count":6,"area":"lr"},{"id":"2510.21285","title":"When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models","created":"2025-10-24","cited_by_count":6,"area":"lr"},{"id":"2606.01498","title":"TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning","created":"2026-05-31","cited_by_count":5,"area":"lr"},{"id":"2606.24526","title":"AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning","created":"2026-06-23","cited_by_count":4,"area":"lr"},{"id":"2512.23328","title":"CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations","created":"2025-12-29","cited_by_count":3,"area":"lr"},{"id":"2504.01789","title":"OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models","created":"2025-04-02","cited_by_count":2,"area":"lr"},{"id":"2509.20616","title":"Training Task Reasoning LLM Agents for Multi-turn Task Planning via Single-turn Reinforcement Learning","created":"2025-09-24","cited_by_count":2,"area":"lr"},{"id":"2602.01709","title":"ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2603.14703","title":"Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization","created":"2026-03-16","cited_by_count":2,"area":"lr"},{"id":"2608.01678","title":"Progressive Agent Skill Generation via Reinforcement Learning","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2505.17106","title":"RRTL: Red Teaming Reasoning Large Language Models in Tool Learning","created":"2025-05-21","cited_by_count":1,"area":"lr"},{"id":"2507.08339","title":"What Factors Affect LLMs and RLLMs in Financial Question Answering?","created":"2025-07-11","cited_by_count":1,"area":"lr"},{"id":"2512.04868","title":"SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs","created":"2025-12-04","cited_by_count":1,"area":"lr"},{"id":"2602.01246","title":"PARSE: An Open-Domain Reasoning Question Answering Benchmark for Persian","created":"2026-02-01","cited_by_count":1,"area":"lr"},{"id":"2604.11025","title":"Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images","created":"2026-04-13","cited_by_count":1,"area":"lr"},{"id":"2604.27859","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"lr"},{"id":"2606.13220","title":"LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis","created":"2026-06-11","cited_by_count":1,"area":"lr"},{"id":"2606.21445","title":"AutoRAS: Learning Robust Agentic Systems with Primitive Representations","created":"2026-06-19","cited_by_count":1,"area":"lr"},{"id":"2609.22228","title":"Assessing Adversarial Robustness of Latent Reasoning Models","created":"2026-09-03","cited_by_count":1,"area":"lr"},{"id":"2508.13382","title":"Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis","created":"2025-08-18","cited_by_count":0,"area":"lr"},{"id":"2605.07699","title":"DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail Domain","created":"2026-05-08","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"}],"next_cursor":null}