llm-kb
← Back to research
Paper

GATS framework eliminates LLM calls during agent planning inference

Researchers propose GATS (Graph-Augmented Tree Search), a planning framework that uses a layered world model and UCB1-based tree search to avoid LLM inference during planning, reducing computational cost and stochasticity. The approach outperforms LATS and ReAct on multi-step planning tasks.

0 engagement·1 source·Thu, Jul 9, 2026, 07:34 PM
The paper introduces GATS, which combines systematic UCB1-based tree search with a three-layer world model: (L1) exact symbolic action matching, (L2) statistics learned from prior trajectories, and (L3) a learned transition model. By eliminating LLM calls during inference, GATS achieves superior planning performance with lower cost and more deterministic behavior compared to LATS and ReAct.

Entities

GATS(tool)LATS(tool)ReAct(tool)UCB1(concept)

Related

PaperFri, Jul 10, 2026, 04:54 PM

Agora paper proposes auction-based task allocation for LLM agents

A new arXiv paper introduces Agora, a framework that uses an incentive-compatible auction mechanism to dynamically allocate tasks to expert LLMs and tools, aiming to improve reasoning performance while accounting for cost and performance variability. The approach addresses limitations in current orchestration methods that rely on coarse-grained function matching.

0 engagement·1 source·arxiv
arXiv
PaperFri, Jul 10, 2026, 08:10 AM

GRACE: Graph-Regularized Agentic Context Evolution for Reliable Long-Horizon LLM Agents

A new arXiv paper proposes GRACE, a method that maintains persistent system-level instructions for LLM agents as a typed semantic graph instead of flat text. This graph-regularized approach enables scoped verification and reliable context evolution over long horizons under distribution shift, addressing verification difficulties from accumulated instructions.

0 engagement·1 source·arxiv
arXiv
PaperSun, Jul 12, 2026, 03:01 AM

Article explains how LLMs use tools and iterate to complete tasks

A technical article titled 'The Agent Loop: How AI Learns to Think, Act, and Get Things Done' describes how LLMs use tools, make decisions, learn from results, and iterate until tasks are complete. The piece provides a conceptual overview of agentic AI workflows.

0 engagement·1 source·rss
RSS
PaperThu, Jul 9, 2026, 06:00 PM

LLM/VLA models enable prompt-driven exploration in RL

A new research paper proposes using large language models (LLMs) and vision-language-action (VLA) models to drive exploration in reinforcement learning by modifying natural language prompts, which induce global behavioral changes beyond standard action noise. This approach could help policies escape weak local optima more effectively.

0 engagement·1 source·arxiv
arXiv
PaperFri, Jul 10, 2026, 04:22 AM

AgentKGV: Agentic LLM-RAG Framework with Two-Stage Training for the Fact Verification of Knowledge Graphs

Researchers propose AgentKGV, an agentic LLM-RAG framework for verifying facts in knowledge graphs. It uses dynamic routing and iterative query rewriting to handle surface-form mismatches in document-level retrieval, and introduces a two-stage training process to improve accuracy and cost-efficiency for industrial deployment.

0 engagement·1 source·arxiv
arXiv