AAAI 2026technical0 citations
SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search
Yifan Zhang, Giridhar Ganapavarapu, Srideepika Jayaraman, Bhavna Agrawal, Dhaval Patel, Achille Fokoue
Abstract
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
BibTeX
@inproceedings{aaai2026_spiralsymbolicll,
title = {SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search},
author = {Yifan Zhang and Giridhar Ganapavarapu and Srideepika Jayaraman and Bhavna Agrawal and Dhaval Patel and Achille Fokoue},
booktitle = {AAAI 2026},
year = {2026}
}