{"total":12,"rows":[{"id":"2604.20987","title":"Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks","created":"2026-04-22","cited_by_count":15,"area":"agents"},{"id":"2605.09650","title":"Workspace Optimization: How to Train Your Agent","created":"2026-05-10","cited_by_count":7,"area":"agents"},{"id":"2605.24539","title":"DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations","created":"2026-05-23","cited_by_count":6,"area":"agents"},{"id":"2605.30931","title":"MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2509.01052","title":"FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games","created":"2025-09-01","cited_by_count":3,"area":"agents"},{"id":"2606.08200","title":"Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents","created":"2026-06-06","cited_by_count":1,"area":"agents"},{"id":"2604.11655","title":"RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.29653","title":"PTCG-Bench: Can LLM Agents Master Pok\\'emon Trading Card Game?","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2608.07490","title":"Experience-Sensitive Game Learning: A Behavioral Study of Humans and Language Agents","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2609.15683","title":"V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environments","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.23142","title":"CraftBench-UE: Deterministic Evaluation for Coding Agents in Unreal Engine","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.34710","title":"FromPitch2Board: Benchmarking LLM Agents in Long-Horizon Football Management","created":"2026-09-28","cited_by_count":0,"area":"agents"}],"next_cursor":null}