PlanGEN：用於生成規劃和推理軌跡的多智能體框架，用於複雜問題解決。

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

February 22, 2025

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

cs.AI

摘要

最近的智能體框架和推論時算法常常在處理複雜規劃問題時遇到困難，這是由於驗證生成計劃或推理以及單個任務中不同複雜度實例的限制。許多現有方法對於這些任務要麼執行任務級驗證而不考慮約束，要麼應用推論時算法而不適應實例級複雜度。為了解決這些限制，我們提出了PlanGEN，這是一個模型無關且易於擴展的智能體框架，具有三個關鍵組件：約束、驗證和選擇智能體。具體來說，我們的方法提出了約束引導的迭代驗證，以增強推論時算法（Best of N、Tree-of-Thought 和 REBASE）的性能。在PlanGEN框架中，選擇智能體基於實例複雜度優化算法選擇，確保更好地適應複雜的規劃問題。實驗結果顯示，在多個基準測試中，我們相對最強基線實現了顯著改進，並在NATURAL PLAN（約8%提升）、OlympiadBench（約4%提升）、DocFinQA（約7%提升）和GPQA（約1%提升）上實現了最新成果。我們的主要發現突顯了約束引導的迭代驗證改善了推論時算法，而自適應選擇進一步提升了在複雜規劃和推理問題上的性能。

English

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 (sim8%uparrow), OlympiadBench (sim4%uparrow), DocFinQA (sim7%uparrow), and GPQA (sim1%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.