@inproceedings{parmar-etal-2025-plangen,
    title = "{P}lan{GEN}: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving",
    author = "Parmar, Mihir  and
      Liu, Xin  and
      Goyal, Palash  and
      Chen, Yanfei  and
      Le, Long  and
      Mishra, Swaroop  and
      Mobahi, Hossein  and
      Gu, Jindong  and
      Wang, Zifeng  and
      Nakhost, Hootan  and
      Baral, Chitta  and
      Lee, Chen-Yu  and
      Pfister, Tomas  and
      Palangi, Hamid",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1042/",
    pages = "20651--20677",
    ISBN = "979-8-89176-332-6",
    abstract = "Recent agent frameworks and inference-time algorithms often struggle with natural planning problems due to limitations in verifying generated plans or reasoning and varying complexity of instances within a single task. Many existing methods for these tasks either perform task-level verification without considering constraints or apply inference-time algorithms without adapting to instance-level complexity. To address these limitations, we propose PlanGEN, a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents. Specifically, our approach proposes constraint-guided iterative verification to enhance performance of inference-time algorithms{--}Best of $\mathcal{N}$, Tree-of-Thought, and REBASE. In PlanGEN framework, the selection agent optimizes algorithm choice based on instance complexity, ensuring better adaptability to complex planning problems. Experimental results demonstrate significant improvements over the strongest baseline across multiple benchmarks, achieving state-of-the-art results on NATURAL PLAN ({\textasciitilde}8{\%}$\uparrow$), OlympiadBench ({\textasciitilde}4{\%}$\uparrow$), DocFinQA ({\textasciitilde}7{\%}$\uparrow$), and GPQA ({\textasciitilde}1{\%}$\uparrow$). Our key finding highlights that constraint-guided iterative verification improves inference-time algorithms, and adaptive selection further boosts performance on complex planning and reasoning problems."
}