{"total":20,"rows":[{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302,"area":"agents"},{"id":"2205.12255","title":"TALM: Tool Augmented Language Models","created":"2022-05-24","cited_by_count":197,"area":"agents"},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2407.15325","title":"Odyssey: Empowering Minecraft Agents with Open-World Skills","created":"2024-07-22","cited_by_count":26,"area":"agents"},{"id":"2506.11045","title":"Procedural Environment Generation for Tool-Use Agents","created":"2025-05-21","cited_by_count":24,"area":"agents"},{"id":"2506.10764","title":"OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems","created":"2025-06-12","cited_by_count":12,"area":"agents"},{"id":"2508.08501","title":"GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games","created":"2025-08-11","cited_by_count":9,"area":"agents"},{"id":"2310.20499","title":"Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models","created":"2023-10-31","cited_by_count":8,"area":"agents"},{"id":"2509.16494","title":"Can an Individual Manipulate the Collective Decisions of Multi-Agents?","created":"2025-09-20","cited_by_count":5,"area":"agents"},{"id":"2601.05899","title":"TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents","created":"2026-01-09","cited_by_count":4,"area":"agents"},{"id":"2606.15899","title":"SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills","created":"2026-06-14","cited_by_count":4,"area":"agents"},{"id":"2605.11269","title":"gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy","created":"2026-05-11","cited_by_count":3,"area":"agents"},{"id":"2509.07389","title":"Talking with Oompa Loompas: A novel framework for evaluating linguistic acquisition of LLM agents","created":"2025-09-09","cited_by_count":1,"area":"agents"},{"id":"2607.27958","title":"$\\Sigma$-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2506.00856","title":"Can AI Master Econometrics? Evidence from Econometrics AI Agent on Expert-Level Tasks","created":"2025-06-01","cited_by_count":0,"area":"agents"},{"id":"2606.25195","title":"SoK: AI Secure Code Generation: Progress, Pitfalls, and Paths Forward","created":"2026-06-23","cited_by_count":0,"area":"agents"},{"id":"2607.26017","title":"UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams","created":"2026-07-28","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"}],"next_cursor":null}