{"total":66,"rows":[{"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":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96,"area":"lr"},{"id":"2505.15107","title":"StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization","created":"2025-05-21","cited_by_count":88,"area":"lr"},{"id":"2505.22019","title":"VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning","created":"2025-05-28","cited_by_count":68,"area":"rag"},{"id":"2508.12752","title":"Deep Research: A Survey of Autonomous Research Agents","created":"2025-08-18","cited_by_count":66,"area":"agents"},{"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":"2510.14967","title":"Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents","created":"2025-10-16","cited_by_count":48,"area":"agents"},{"id":"2505.11277","title":"Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning","created":"2025-05-16","cited_by_count":35,"area":"lr"},{"id":"2504.10147","title":"A Survey of Personalization: From RAG to Agent","created":"2025-04-14","cited_by_count":27,"area":"rag"},{"id":"2504.15909","title":"Synergizing RAG and Reasoning: A Systematic Review","created":"2025-04-22","cited_by_count":27,"area":"lr"},{"id":"2509.20758","title":"SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs","created":"2025-09-25","cited_by_count":24,"area":null},{"id":"2602.02488","title":"RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System","created":"2026-02-02","cited_by_count":24,"area":"agents"},{"id":"2506.10408","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","created":"2025-06-12","cited_by_count":19,"area":"lr"},{"id":"2509.12867","title":"Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use","created":"2025-09-16","cited_by_count":16,"area":"agents"},{"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":"2505.24105","title":"Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning","created":"2025-05-30","cited_by_count":14,"area":"lr"},{"id":"2512.22560","title":"RollArt: Disaggregated Multi-Task Agentic RL Training at Scale","created":"2025-12-27","cited_by_count":14,"area":"agents"},{"id":"2601.04888","title":"SmartSearch: Process Reward-Guided Query Refinement for Search Agents","created":"2026-01-08","cited_by_count":14,"area":"agents"},{"id":"2505.17767","title":"Position: The Real Barrier to LLM Agent Usability is Agentic ROI","created":"2025-05-23","cited_by_count":12,"area":"agents"},{"id":"2605.10899","title":"RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards","created":"2026-05-11","cited_by_count":12,"area":"agents"},{"id":"2506.11603","title":"TongSearch-QR: Reinforced Query Reasoning for Retrieval","created":"2025-06-13","cited_by_count":11,"area":"lr"},{"id":"2506.08125","title":"Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning","created":"2025-06-09","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":"2504.11001","title":"ReZero: Enhancing LLM search ability by trying one-more-time","created":"2025-04-15","cited_by_count":9,"area":"rag"},{"id":"2510.14321","title":"Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2605.22511","title":"Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning","created":"2026-05-21","cited_by_count":9,"area":"lr"},{"id":"2506.02911","title":"Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning","created":"2025-06-03","cited_by_count":8,"area":"lr"},{"id":"2508.08137","title":"MuaLLM: A Multimodal Large Language Model Agent for Circuit Design Assistance with Hybrid Contextual Retrieval-Augmented Generation","created":"2025-08-11","cited_by_count":8,"area":"mllm"},{"id":"2509.10697","title":"A Survey on Retrieval And Structuring Augmented Generation with Large Language Models","created":"2025-09-12","cited_by_count":8,"area":null},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2510.15339","title":"AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction","created":"2025-10-17","cited_by_count":7,"area":"lr"},{"id":"2601.21257","title":"MoCo: A One-Stop Shop for Model Collaboration Research","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2601.21340","title":"EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generation","created":"2026-01-29","cited_by_count":6,"area":"rag"},{"id":"2511.07581","title":"Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models","created":"2025-11-10","cited_by_count":5,"area":"lr"},{"id":"2508.21104","title":"PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning","created":"2025-08-28","cited_by_count":4,"area":"agents"},{"id":"2605.26567","title":"MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning","created":"2026-05-26","cited_by_count":4,"area":"lr"},{"id":"2505.23667","title":"Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"lr"},{"id":"2510.17139","title":"Rethinking On-policy Optimization for Query Augmentation","created":"2025-10-20","cited_by_count":3,"area":"lr"},{"id":"2509.04820","title":"Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation","created":"2025-09-05","cited_by_count":2,"area":"rag"},{"id":"2605.26352","title":"RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents","created":"2026-05-25","cited_by_count":2,"area":"lr"},{"id":"2606.07299","title":"DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning","created":"2026-06-05","cited_by_count":2,"area":"agents"},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.16316","title":"RL-Index: Reinforcement Learning for Retrieval Index Reasoning","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2607.05794","title":"From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space","created":"2026-07-07","cited_by_count":2,"area":null},{"id":"2608.02407","title":"Antares: Foundation Models for Agentic Vulnerability Localization","created":"2026-08-03","cited_by_count":2,"area":"agents"},{"id":"2609.00638","title":"It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning","created":"2026-09-01","cited_by_count":2,"area":"lr"},{"id":"2506.19783","title":"SAGE: Strategy-Adaptive Generation Engine for Query Rewriting","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2510.18659","title":"Sherlock Your Queries: Learning to Ask the Right Questions for Dialogue-Based Retrieval","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2601.17006","title":"MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning","created":"2026-01-14","cited_by_count":1,"area":"lr"},{"id":"2602.13179","title":"Fix Before Search: Benchmarking Agentic Query Visual Pre-processing in Multimodal Retrieval-augmented Generation","created":"2026-02-13","cited_by_count":1,"area":"rag"},{"id":"2604.05818","title":"WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2605.00505","title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","created":"2026-05-01","cited_by_count":1,"area":"rag"},{"id":"2609.39148","title":"Do Self-Evolving Skills Generalize to Held-Out Tasks?","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2510.04096","title":"RLRF: Competitive Search Agent Design via Reinforcement Learning from Ranker Feedback","created":"2025-10-05","cited_by_count":0,"area":"agents"},{"id":"2603.06397","title":"Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.17387","title":"CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrieval","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.07201","title":"BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.14967","title":"UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards","created":"2026-04-16","cited_by_count":0,"area":"mllm"},{"id":"2605.09038","title":"SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.28566","title":"R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2608.00030","title":"SLMs as Multi-Agent Routers: A Progressive SFT and Reinforcement Learning Approach","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2608.19595","title":"SSR-GRPO: Integrating Supervision and Semantic IDs into Reinforcement Learning for Dense Retrieval in E-commerce","created":"2026-08-20","cited_by_count":0,"area":"lr"},{"id":"2609.33119","title":"MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.13335","title":"AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.17827","title":"Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents","created":"2026-10-13","cited_by_count":0,"area":"alignment"}],"next_cursor":null}