{"total":22,"rows":[{"id":"2512.13564","title":"Memory in the Age of AI Agents","created":"2025-12-15","cited_by_count":303,"area":"agents"},{"id":"2602.07274","title":"TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents","created":"2026-02-06","cited_by_count":29,"area":"agents"},{"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":"2606.19659","title":"SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation","created":"2026-06-17","cited_by_count":15,"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":"2601.05930","title":"Can We Predict Before Executing Machine Learning Agents?","created":"2026-01-09","cited_by_count":10,"area":"agents"},{"id":"2605.29801","title":"AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security","created":"2026-05-28","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":"2604.27955","title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","created":"2026-04-30","cited_by_count":3,"area":"agents"},{"id":"2604.04373","title":"Decocted Experience Improves Test-Time Inference in LLM Agents","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2608.22631","title":"Learning Generalizable Behaviors for Terminal Agents","created":"2026-08-23","cited_by_count":2,"area":"agents"},{"id":"2608.10299","title":"Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2609.05576","title":"EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2610.11345","title":"SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning","created":"2026-10-08","cited_by_count":1,"area":"agents"},{"id":"2609.08404","title":"Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.22592","title":"AutoGym: Blueprint-First Generation of Verifiable Agent Gyms","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.32750","title":"CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.34321","title":"One Rollout Is All You Get: Fully Test-Time Adaptation for GUI Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.39325","title":"WorkGenesis: Building the Worlds That Teach Agents to Work","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.12593","title":"Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.14774","title":"ProgAgent: Learning Tool Orchestration through Programmatic Training","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.20597","title":"Co-Evolving Acting and Forecasting for Language Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}