GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
Quick Answer
This paper shows that GATS (Graph-Augmented Tree Search) outperforms LATS and ReAct in multi-step planning tasks, achieving a 100% success rate without LLM calls.
Quick Take
GATS (Graph-Augmented Tree Search) outperforms LATS and ReAct in multi-step planning tasks, achieving a 100% success rate without LLM calls. It utilizes a three-layer world model for deterministic planning, contrasting with LATS's 37 LLM calls per task and ReAct's stochastic behavior.
Key Points
- GATS achieves 100% success on synthetic tasks, outperforming LATS (92%) and ReAct (64%).
- In 12 challenging scenarios, GATS maintains 100% success, while LATS drops to 88.9% and ReAct to 23.9%.
- GATS requires zero LLM calls per task, compared to 37 for LATS.
- The framework integrates symbolic action matching, execution log statistics, and LLM-based predictions.
- GATS produces deterministic plans with zero variance across runs.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Agent Tree Search) and ReAct rely heavily on LLM inference during planning, leading to high computational costs and stochastic behavior. We present \textbf{GATS} (Graph-Augmented Tree Search), a planning framework that combines systematic UCB1-based tree search with a layered world model to eliminate LLM calls during inference while achieving superior planning performance. Our three-layer world model integrates: (L1) exact symbolic action matching, (L2) statistics learned from execution logs, and (L3) LLM-based prediction for unknown actions. On synthetic planning tasks with branching paths and dead-ends, GATS achieves \textbf{100\% success rate} compared to 92 % for LATS and 64\% for ReAct. On a comprehensive stress test spanning 12 challenging scenarios -- including coding workflows, web navigation, and long-horizon tasks -- GATS maintains \textbf{100\% success} while LATS drops to 88.9 % and ReAct to 23.9%. GATS requires \textbf{zero LLM calls per task} during planning (vs. 37 per task for LATS) and produces deterministic plans with zero variance across runs. Our results demonstrate that systematic search with learned world models can substantially outperform LLM-guided exploration for agent planning.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2607.08894 [cs.AI] |
| (or arXiv:2607.08894v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.08894 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dimitri Nowicki [view email]
[v1]
Thu, 9 Jul 2026 19:34:29 UTC (17 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Adversarial Social Epistemology for Assemblies of Humans and Large Language Models
The paper introduces Adversarial Social Epistemology (ASE) to analyze how agents manipulate trust in public communications, highlighting mechanisms that undermine the reliability of testimony and inference. It critiques existing frameworks like epistemic bubbles and misinformation diffusion, proposing a new language for understanding trust breaches and auditing inferential chains in densely interactive environments involving humans and large language models.