arXiv：cs.AI· Hong Lu, Pierrick Lorang, Timothy R. Duggan, Jivko Sinapov, Matthias Scheutz·· 4 小时前AI 评分35
混合 LLM-符号规划与 LLM 引导强化学习实现新颖性适应
Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning
AI 导读
研究者提出一种神经符号架构，将符号规划、强化学习与 LLM 结合，利用 LLM 的常识推理识别缺失算子、生成规划并编写奖励函数，引导强化学习智能体学习新算子的控制策略。该方法在连续机器人任务中的算子发现与算子学习上均优于现有最优方法，论文已被 IROS 2026 接收。
正文
Abstract:In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals. Specifically, traditional symbolic planners fail to generate plans when the robot's planning domain lacks the operators that enable it to interact appropriately with novel objects in the environment. We propose a neuro-symbolic architecture that integrates symbolic planning, reinforcement learning, and a large language model (LLM) to learn how to handle novel objects. In particular, we leverage the common sense reasoning capability of the LLM to identify missing operators, generate plans with the symbolic AI planner, and write reward functions to guide the reinforcement learning agent in learning control policies for newly identified operators. Our method outperforms the state-of-the-art methods in operator discovery as well as operator learning in continuous robotic this http URL webpage and code can be access here: this https URL
| Comments: | Accepted at IEEE/RSJ International Conference on Intelligent Robots & Systems (IROS) 2026 |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.11351 [cs.RO] |
| (or arXiv:2603.11351v3 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2603.11351 arXiv-issued DOI via DataCite |
Submission history
From: Pierrick Lorang [view email]
[v1]
Wed, 11 Mar 2026 22:38:05 UTC (4,839 KB)
[v2]
Wed, 23 Sep 2026 19:56:05 UTC (5,148 KB)
[v3]
Fri, 2 Oct 2026 06:30:34 UTC (5,148 KB)
来源：arXiv：cs.AI · arxiv.org