arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.16111cs.AIcs.CL
收藏

PlanGEN:一种用于生成复杂问题求解的规划与推理轨迹的多智能体框架

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving

Google(谷歌);Arizona State University(亚利桑那州立大学)
Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long Le, Swaroop Mishra, Hossein Mobahi, Jindong Gu, Zifeng Wang, Hootan Nakhost, Chitta Baral, Chen-Yu Lee, T… 展开作者

Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long Le, Swaroop Mishra, Hossein Mobahi, Jindong Gu, Zifeng Wang, Hootan Nakhost, Chitta Baral, Chen-Yu Lee, Tomas Pfister, Hamid Palangi

AI总结:

PlanGEN是一个多智能体框架,通过约束引导的迭代验证和自适应算法选择,显著提升了复杂规划与推理问题的求解性能。

摘要:

现有的智能体框架和推理时间算法在处理复杂规划问题时往往面临挑战,原因在于验证生成的规划或推理过程存在局限,以及单个任务中实例复杂度的差异性。许多现有方法要么执行任务级验证而不考虑约束条件,要么应用推理时间算法而不适应实例级复杂度。为解决这些局限,我们提出了PlanGEN,一个与模型无关且易于扩展的智能体框架,包含三个关键组件:约束智能体、验证智能体和选择智能体。具体而言,我们的方法提出约束引导的迭代验证,以增强推理时间算法(Best of N、思维树和REBASE)的性能。在PlanGEN框架中,选择智能体根据实例复杂度优化算法选择,确保对复杂规划问题具有更好的适应性。实验结果表明,在多个基准上相比最强基线有显著提升,在NATURAL PLAN(约8%提升)、OlympiadBench(约4%提升)、DocFinQA(约7%提升)和GPQA(约1%提升)上取得了最先进的结果。我们的关键发现强调,约束引导的迭代验证改进了推理时间算法,而自适应选择进一步提升了复杂规划和推理问题的性能。

英文摘要:

Recent agent frameworks and inference-time algorithms often struggle with complex 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 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 ($\sim$8%$\uparrow$), OlympiadBench ($\sim$4%$\uparrow$), DocFinQA ($\sim$7%$\uparrow$), and GPQA ($\sim$1%$\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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑