Agents are commonly instructed to follow a task-specific plan for guidance. However, it is unknown to what extent agents actually follow instructed plans. Without such an analysis, determining the extent agents comply with a given plan, it is impossible to assess whether a solution was reached through correct strategic reasoning or through other means, e.g., data contamination or overfitting to a benchmark. This paper presents the first extensive, systematic analysis of plan compliance in programming agents, examining 21,120 trajectories from SWE-agent across four LLMs on SWE-bench Verified and SWE-bench Pro under eight plan variations. Without an explicit plan, agents fall back on internalized workflows during training, which are often incomplete, overfit, or inconsistently applied. Providing the standard plan improves issue resolution, and we observe that periodic plan reminders can mitigate plan violations and improve task success. A subpar plan hurts performance even more than no plan at all. Surprisingly, inserting additional task-relevant phases in the early stage can degrade performance, particularly when these phases do not align with the model's internal problem-solving strategy. These findings call for fine-tuning paradigms that teach models to follow instructed plans, rather than encoding task-specific plans in them, so that they reason and act adaptively, rather than memorizing workflows.
Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents
Tongji University(同济大学);Shanghai AI Laboratory(上海人工智能实验室);Harbin Institute of Technology(哈尔滨工业大学);Fudan University(复旦大学);Skywork AI;University of California, Santa Cruz(加州大学圣克鲁兹分校);Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学)
MPO: Boosting LLM Agents with Meta Plan Optimization
Key Laboratory of Computational Linguistics, Ministry of Education, School of Computer Science, Peking University(北京大学计算机学院教育部计算语言学重点实验室);University of Washington(华盛顿大学);Microsoft(微软)
Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agents
Concordia University(康科德大学);Mila - Quebec AI Institute(魁北克人工智能研究所);University of Copenhagen(哥本哈根大学);Universite Claude Bernard Lyon(克莱尔蒙特-伯恩大学);McGill University(麦吉尔大学)
SOTOPIA-$Ω$: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)