cd /news/artificial-intelligence/gats-graph-augmented-tree-search-wit… · home topics artificial-intelligence article
[ARTICLE · art-56784] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning

Researchers introduced GATS (Graph-Augmented Tree Search), a planning framework that uses UCB1-based tree search with a layered world model to eliminate LLM calls during inference. GATS achieved 100% success rate on synthetic planning tasks and maintained 100% success across 12 challenging scenarios, outperforming LATS (88.9%) and ReAct (23.9%) while requiring zero LLM calls per task. The framework demonstrates that systematic search with learned world models can surpass LLM-guided exploration for agent planning.

read1 min views1 publishedJul 13, 2026

arXiv:2607.08894v1 Announce Type: new Abstract: 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.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @gats 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/gats-graph-augmented…] indexed:0 read:1min 2026-07-13 ·