EUVIMEDEUVIMED entdecken
Crossref

MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization

Jian Zhang, Zhangqi Wang, Haiping Zhu, Kangda Cheng, Kai He, Bo Li, Qika Lin, Jun Liu, Erik Cambria

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (19) · 16307-16315

DOI: 10.1609/aaai.v40i19.38668 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jian Zhang und 8 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) typically operate in a question-answering paradigm, where the quality of the input prompt critically affects the response. Automated Prompt Optimization (APO) aims to overcome the cognitive biases of manually crafted prompts and explore a broader prompt design space. However, existing APO methods often suffer from rigid template structures and inefficient exploration in the prompt space. To this end, we propose a Multi-Agent Adaptive Reasoning with Socratic guidance framework (MARS) for APO. MARS consists of five complementary agents and formulates the optimization process as a Partially Observable Markov Decision Process (POMDP), enabling adaptive prompt refinement through explicit state modeling and interactive feedback. Specifically, a Planner agent generates flexible optimization trajectories, a Teacher-Critic-Student triad engages in Socratic-style dialogue to iteratively optimize the prompt based on pseudo-gradient signals in the text space, and a Target agent executes the prompt in downstream tasks to provide performance feedback. MARS integrates reasoning, feedback, and state transition into a unified hidden-state evolution process, improving both the effectiveness and interpretability of optimization. Extensive experiments on multiple datasets demonstrate that MARS outperforms existing APO methods in terms of optimization performance, search efficiency, and interpretability.

Zitieren

APA

Zhang, J., Wang, Z., Zhu, H., Cheng, K., He, K., Li, B., Lin, Q., Liu, J., & Cambria, E. (2026). MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization. Proceedings of the AAAI Conference on Artificial Intelligence, 40(19), 16307-16315. https://doi.org/10.1609/aaai.v40i19.38668

Vancouver

Zhang J, Wang Z, Zhu H, Cheng K, He K, Li B, et al. MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(19):16307-16315. doi:10.1609/aaai.v40i19.38668

BibTeX
@article{Zhang2026,
  author = {Zhang, Jian and Wang, Zhangqi and Zhu, Haiping and Cheng, Kangda and He, Kai and Li, Bo and Lin, Qika and Liu, Jun and Cambria, Erik},
  title = {MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {19},
  pages = {16307--16315},
  doi = {10.1609/aaai.v40i19.38668}
}
Kostenlos starten →