EUVIMEDEUVIMED entdecken
Crossref

NL2CA: Auto-formalizing Cognitive Decision-Making from Natural Language Using an Unsupervised CriticNL2LTL Framework

Zihao Deng, Yijia Li, Renrui Zhang, Peijun Ye

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (3) · 1766-1773

DOI: 10.1609/aaai.v40i3.37155 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zihao Deng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cognitive computing models offer a formal and interpretable way to characterize human's deliberation and decision-making, yet their development remains labor-intensive. In this paper, we propose NL2CA, a novel method for auto-formalizing cognitive decision-making rules from natural language descriptions of human experience. Different from most related work that exploits either pure manual or human-guided interactive modeling, our method is fully automated without any human intervention. The approach first translates text into Linear Temporal Logic (LTL) using a fine-tuned large language model (LLM), then refines the logic via an unsupervised Critic Tree, and finally transforms the output into executable production rules compatible with symbolic cognitive frameworks. Based on the resulted rules, a cognitive agent is further constructed and optimized through cognitive reinforcement learning according to the real-world behavioral data. Our method is validated in two domains: (1) NL-to-LTL translation, where our CriticNL2LTL module achieves consistent performance across both expert and large-scale benchmarks without human-in-the-loop feedbacks, and (2) cognitive driving simulation, where agents automatically constructed from human interviews have successfully learned the diverse decision patterns of about 70 trials in different critical scenarios. Experimental results demonstrate that NL2CA enables scalable, interpretable, and human-aligned cognitive modeling from unstructured textual data, offering a novel paradigm to automatically design symbolic cognitive agents.

Zitieren

APA

Deng, Z., Li, Y., Zhang, R., & Ye, P. (2026). NL2CA: Auto-formalizing Cognitive Decision-Making from Natural Language Using an Unsupervised CriticNL2LTL Framework. Proceedings of the AAAI Conference on Artificial Intelligence, 40(3), 1766-1773. https://doi.org/10.1609/aaai.v40i3.37155

Vancouver

Deng Z, Li Y, Zhang R, Ye P. NL2CA: Auto-formalizing Cognitive Decision-Making from Natural Language Using an Unsupervised CriticNL2LTL Framework. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(3):1766-1773. doi:10.1609/aaai.v40i3.37155

BibTeX
@article{Deng2026,
  author = {Deng, Zihao and Li, Yijia and Zhang, Renrui and Ye, Peijun},
  title = {NL2CA: Auto-formalizing Cognitive Decision-Making from Natural Language Using an Unsupervised CriticNL2LTL Framework},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {3},
  pages = {1766--1773},
  doi = {10.1609/aaai.v40i3.37155}
}
Kostenlos starten →