
JZ
Jiaxing Zhao, Hanwen Wang, Di Liu, Shaoteng Liu, Jing-Ran Su, Yanheng Li, Qian Zha, Jiaxi Li, Hongbin Xie, Haoran Zhang, Xuan Song, Haoxuan Che
· 1 min read
ResearcharXiv cs.CL
MetaAct: Self-Evolving Executable Action Constraints for Embodied Language Agents
arXiv:2611.20655v1 Announce Type: new
Abstract: Self-evolving language agents have emerged as a promising paradigm for continuously improving agent behavior through experience. However, most existing approaches evolve textual artifacts, which can influence action preferences but cannot reliably enforce action admissibility in embodied environments with discrete and often irreversible actions. We propose MetaAct, which shifts self-evolution from textual guidance to executable action constraints by synthesizing GEAR (Grounded Executable Action Rules) from execution feedback. Each rule is represented as a typed specification, compiled into a deterministic guard, and validated offline through trajectory replay without additional model calls or environment interactions. Across four benchmarks, MetaAct improves task performance; on ScienceWorld and WebShop, violations drop from 70% to 0% and 40% to 1%, with score gains of +10.1 and +8.0. Our code is available at https://github.com/BaiCubed/MetaAct.
Original source
This story was published by arXiv cs.CL and written by Jiaxing Zhao, Hanwen Wang, Di Liu, Shaoteng Liu, Jing-Ran Su, Yanheng Li, Qian Zha, Jiaxi Li, Hongbin Xie, Haoran Zhang, Xuan Song, Haoxuan Che. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


