{"total":40,"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":"2509.24704","title":"MemGen: Weaving Generative Latent Memory for Self-Evolving Agents","created":"2025-09-29","cited_by_count":109,"area":"agents"},{"id":"2509.21240","title":"Tree Search for LLM Agent Reinforcement Learning","created":"2025-09-25","cited_by_count":79,"area":"agents"},{"id":"2510.25445","title":"Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions","created":"2025-10-29","cited_by_count":48,"area":"agents"},{"id":"2508.18669","title":"MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use","created":"2025-08-26","cited_by_count":32,"area":"agents"},{"id":"2509.19736","title":"UserRL: Training Interactive User-Centric Agent via Reinforcement Learning","created":"2025-09-24","cited_by_count":32,"area":"agents"},{"id":"2509.25238","title":"PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure Cases","created":"2025-09-25","cited_by_count":22,"area":"agents"},{"id":"2605.07725","title":"SOD: Step-wise On-policy Distillation for Small Language Model Agents","created":"2026-05-08","cited_by_count":21,"area":"agents"},{"id":"2510.10197","title":"Don't Just Fine-tune the Agent, Tune the Environment","created":"2025-10-11","cited_by_count":19,"area":"agents"},{"id":"2509.17325","title":"Generalizable End-to-End Tool-Use RL with Synthetic CodeGym","created":"2025-09-22","cited_by_count":17,"area":"agents"},{"id":"2509.21842","title":"DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents","created":"2025-09-26","cited_by_count":17,"area":"agents"},{"id":"2601.14192","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","created":"2026-01-20","cited_by_count":16,"area":"agents"},{"id":"2512.04535","title":"GTM: Simulating the World of Tools for AI Agents","created":"2025-12-04","cited_by_count":14,"area":"agents"},{"id":"2605.18396","title":"NEWTON: Agentic Planning for Physically Grounded Video Generation","created":"2026-05-18","cited_by_count":12,"area":"agents"},{"id":"2509.22601","title":"Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning","created":"2025-09-26","cited_by_count":11,"area":"agents"},{"id":"2604.04872","title":"Synthetic Sandbox for Training Machine Learning Engineering Agents","created":"2026-04-06","cited_by_count":11,"area":"agents"},{"id":"2512.01311","title":"CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL","created":"2025-12-01","cited_by_count":10,"area":"agents"},{"id":"2602.01675","title":"TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios","created":"2026-02-02","cited_by_count":10,"area":"agents"},{"id":"2510.16720","title":"Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI","created":"2025-10-19","cited_by_count":8,"area":"agents"},{"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":"2512.10534","title":"Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning","created":"2025-12-11","cited_by_count":7,"area":"agents"},{"id":"2605.00737","title":"To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling","created":"2026-05-01","cited_by_count":7,"area":"agents"},{"id":"2509.23206","title":"PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness","created":"2025-09-27","cited_by_count":4,"area":"agents"},{"id":"2512.02228","title":"STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Calls","created":"2025-12-01","cited_by_count":4,"area":"agents"},{"id":"2601.15141","title":"CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning","created":"2026-01-21","cited_by_count":4,"area":"agents"},{"id":"2603.06713","title":"Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces","created":"2026-03-05","cited_by_count":4,"area":"agents"},{"id":"2607.24850","title":"SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task","created":"2026-07-25","cited_by_count":3,"area":"agents"},{"id":"2511.11770","title":"Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction","created":"2025-11-14","cited_by_count":2,"area":"agents"},{"id":"2602.11351","title":"Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization","created":"2026-02-11","cited_by_count":2,"area":"agents"},{"id":"2601.17332","title":"TheoremForge: Scaling up Formal Data Synthesis with Low-Budget Agentic Workflow","created":"2026-01-24","cited_by_count":1,"area":"agents"},{"id":"2602.19218","title":"Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls","created":"2026-02-22","cited_by_count":1,"area":"agents"},{"id":"2603.16876","title":"Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation","created":"2026-02-17","cited_by_count":1,"area":"agents"},{"id":"2603.21630","title":"EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises","created":"2026-03-23","cited_by_count":1,"area":"agents"},{"id":"2606.03762","title":"Tool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2607.14145","title":"ToolAnchor: Anchoring Counterfactual Context to Boost Agentic Tool-use Capability","created":"2026-07-14","cited_by_count":1,"area":"agents"},{"id":"2602.00766","title":"Communications-Incentivized Collaborative Reasoning in NetGPT through Agentic Reinforcement Learning","created":"2026-01-31","cited_by_count":0,"area":"agents"},{"id":"2605.08399","title":"CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2605.13579","title":"Position: Assistive Agents Need Accessibility Alignment","created":"2026-05-13","cited_by_count":0,"area":"agents"},{"id":"2605.14051","title":"SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks","created":"2026-05-13","cited_by_count":0,"area":"agents"},{"id":"2607.13396","title":"Set-shifting Behavioral Test for Harnessed Agents","created":"2026-07-15","cited_by_count":0,"area":"agents"}],"next_cursor":null}