SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (43) · 36527-36535
DOI: 10.1609/aaai.v40i43.40975 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yifan Zhang und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Large Language Models (LLMs) often falter at complex planning tasks that require exploration and self-correction, as their linear reasoning process struggles to recover from early mistakes. While search algorithms like Monte Carlo Tree Search (MCTS) can explore alternatives, they are often ineffective when guided by sparse rewards and fail to leverage the rich semantic capabilities of LLMs. We introduce SPIRAL (Symbolic LLM Planning via Grounded and Reflective Search), a novel framework that embeds a cognitive architecture of three specialized LLM agents into an MCTS loop. SPIRAL's key contribution is its integrated planning pipeline where a Planner proposes creative next steps, a Simulator grounds the search by predicting realistic outcomes, and a Critic provides dense reward signals through reflection. This synergy transforms MCTS from a brute-force search into a guided, self-correcting reasoning process. On the DailyLifeAPIs and HuggingFace datasets, SPIRAL consistently outperforms the default Chain-of-Thought planning method and other state-of-the-art agents. More importantly, it substantially surpasses other state-of-the-art agents; for example, SPIRAL achieves 83.6% overall accuracy on DailyLifeAPIs, an improvement of over 16 percentage points against the next-best search framework, while also demonstrating superior token efficiency. Our work demonstrates that structuring LLM reasoning as a guided, reflective, and grounded search process yields more robust and efficient autonomous planners. The source code, full appendices, and all experimental data are available for reproducibility at the official project repository.
Zitieren
APA
Zhang, Y., Ganapavarapu, G., Jayaraman, S., Agrawal, B., Patel, D., & Fokoue, A. (2026). SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search. Proceedings of the AAAI Conference on Artificial Intelligence, 40(43), 36527-36535. https://doi.org/10.1609/aaai.v40i43.40975
Vancouver
Zhang Y, Ganapavarapu G, Jayaraman S, Agrawal B, Patel D, Fokoue A. SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(43):36527-36535. doi:10.1609/aaai.v40i43.40975
BibTeX
@article{Zhang2026,
author = {Zhang, Yifan and Ganapavarapu, Giridhar and Jayaraman, Srideepika and Agrawal, Bhavna and Patel, Dhaval and Fokoue, Achille},
title = {SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {43},
pages = {36527--36535},
doi = {10.1609/aaai.v40i43.40975}
}
EUVIMED