Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs) frequently generate plans that violate task constraints, undermining their reliability in real-world applications. This deficiency arises from a lack of systematic mechanisms to incorporate constraint information during the generation process.
arXiv:2607. 04854v1 Announce Type: new Abstract: Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs) frequently generate plans that violate task constraints, undermining their reliability in real-world applications.
By Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu
The paper presents a reinforcement learning method, HSAC, that builds covering structures without relying on rigid, pre‑planned sequences. It uses graph‑structured state representations and a mixed action space to select blocks and adjust their placement continuously, while an efficient exploration strategy incorporates unilateral edges into graph neural networks. HSAC outperforms the prior hybrid‑PPO approach, shows strong sample efficiency, robustness to hyperparameters, and successfully transfers policies from simulation to a real two‑robot 3D‑printed block construction task.
Recent advances in generative planning have made trajectory inpainting a promising approach to offline goal-conditioned reinforcement learning. However, these methods typically specify the planning ho...
arXiv:2606. 30940v1 Announce Type: cross Abstract: Deep learning methods have vastly expanded the capabilities of motion planning in robotics applications, as learning priors from large-scale data has been shown to be essential in capturing the highly complex behavior required for solving tasks such as manipulation or navigation for autonomous vehicles.
By Lukas Lao Beyer, Sertac Karaman
HorizonFlow is a hierarchical planner for offline goal-conditioned reinforcement learning that treats the planning horizon as an output rather than a fixed input. It uses a subgoal route planner and an action-prefix controller, both employing insertion-based generation and flow matching, to jointly generate continuous plan content and its length. The method leverages the partially generated plan to guide token insertion and to steer generation toward shorter plans, achieving superior performance on Maze2D, Multi2D, and OGBench benchmarks.
By JunHyeok Oh, Zian Jang, Byung-Jun Lee