Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents

본문 미리보기

arXiv:2607.05775v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and operate over extended horizons. Reported benchmark gains often obscure recurring failure modes documented across otherwise unrelated evaluation efforts. This paper synthesizes 27 benchmark, taxonomy, and audit papers (2023-2026), spanning 19 distinct benchmarks, into a cross-cutting taxonomy of agent