{"total":25,"rows":[{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2505.23885","title":"OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation","created":"2025-05-29","cited_by_count":131,"area":"lr"},{"id":"2512.17102","title":"Reinforcement Learning for Self-Improving Agent with Skill Library","created":"2025-12-18","cited_by_count":100,"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":"2601.11100","title":"ReCreate: Reasoning and Creating Domain Agents Driven by Experience","created":"2026-01-16","cited_by_count":24,"area":"lr"},{"id":"2410.04526","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","created":"2024-10-06","cited_by_count":20,"area":"lr"},{"id":"2603.11682","title":"Entropy-Preserving Reinforcement Learning","created":"2026-03-12","cited_by_count":11,"area":"lr"},{"id":"2606.03854","title":"CLI-Anything: Towards Agent-Native Computer Use","created":"2026-06-02","cited_by_count":9,"area":"lr"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2506.12012","title":"Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making","created":"2025-06-13","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2606.18810","title":"Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards","created":"2026-06-17","cited_by_count":4,"area":"lr"},{"id":"2608.24747","title":"SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents","created":"2026-08-25","cited_by_count":4,"area":"lr"},{"id":"2608.01667","title":"TCPO: Turn-Level Credit Policy Optimization","created":"2026-08-03","cited_by_count":3,"area":"lr"},{"id":"2510.08567","title":"MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning","created":"2025-10-09","cited_by_count":1,"area":"lr"},{"id":"2605.07251","title":"Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2509.21998","title":"GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments","created":"2025-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.27276","title":"DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.30906","title":"ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.31906","title":"EmailBench: A Benchmark for Evaluating LLM Agents on Enterprise Email and Productivity Tasks","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.35082","title":"Cross-Rollout Bellman Closure for Long-Horizon Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.18683","title":"ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.19349","title":"Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}