Paper
Agentic Self-Evolutionary Replanning for Embodied Navigation
Authors
Guoliang Li, Ruihua Han, Chengyang Li, He Li, Shuai Wang, Wenchao Ding, Hong Zhang, Chengzhong Xu
Abstract
Failure is inevitable for embodied navigation in complex environments. To enhance the resilience, replanning (RP) is a viable option, where the robot is allowed to fail, but is capable of adjusting plan until success. However, existing RP approaches freeze the ego action model and miss the opportunities to explore better plans by upgrading the robot itself. To address this limitation, we propose Self-Evolutionary RePlanning, or SERP for short, which leads to a paradigm shift from frozen models towards evolving models by run-time learning from recent experiences. In contrast to existing model evolution approaches that often get stuck at predefined static parameters, we introduce agentic self-evolving action model that uses in-context learning with auto-differentiation (ILAD) for adaptive function adjustment and global parameter reset. To achieve token-efficient replanning for SERP, we also propose graph chain-of-thought (GCOT) replanning with large language model (LLM) inference over distilled graphs. Extensive simulation and real-world experiments demonstrate that SERP achieves higher success rate with lower token expenditure over various benchmarks, validating its superior robustness and efficiency across diverse environments.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.02772v1</id>\n <title>Agentic Self-Evolutionary Replanning for Embodied Navigation</title>\n <updated>2026-03-03T09:12:29Z</updated>\n <link href='https://arxiv.org/abs/2603.02772v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.02772v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Failure is inevitable for embodied navigation in complex environments. To enhance the resilience, replanning (RP) is a viable option, where the robot is allowed to fail, but is capable of adjusting plan until success. However, existing RP approaches freeze the ego action model and miss the opportunities to explore better plans by upgrading the robot itself. To address this limitation, we propose Self-Evolutionary RePlanning, or SERP for short, which leads to a paradigm shift from frozen models towards evolving models by run-time learning from recent experiences. In contrast to existing model evolution approaches that often get stuck at predefined static parameters, we introduce agentic self-evolving action model that uses in-context learning with auto-differentiation (ILAD) for adaptive function adjustment and global parameter reset. To achieve token-efficient replanning for SERP, we also propose graph chain-of-thought (GCOT) replanning with large language model (LLM) inference over distilled graphs. Extensive simulation and real-world experiments demonstrate that SERP achieves higher success rate with lower token expenditure over various benchmarks, validating its superior robustness and efficiency across diverse environments.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n <published>2026-03-03T09:12:29Z</published>\n <arxiv:comment>8 pages, 10 figures, 4 tables, submitted to IEEE for possible publication</arxiv:comment>\n <arxiv:primary_category term='cs.RO'/>\n <author>\n <name>Guoliang Li</name>\n </author>\n <author>\n <name>Ruihua Han</name>\n </author>\n <author>\n <name>Chengyang Li</name>\n </author>\n <author>\n <name>He Li</name>\n </author>\n <author>\n <name>Shuai Wang</name>\n </author>\n <author>\n <name>Wenchao Ding</name>\n </author>\n <author>\n <name>Hong Zhang</name>\n </author>\n <author>\n <name>Chengzhong Xu</name>\n </author>\n </entry>"
}