GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks
Jianwen Luo, Yiming Huang, Jinxiang Meng, Fangyu Lei, Shizhu He, Xiao, Liu, Shanshan Jiang, Bin Dong, Jun Zhao, Kang Liu

TL;DR
GATE is an adaptive framework that dynamically constructs and evolves hierarchical toolsets for diverse tasks, significantly improving efficiency and performance over existing methods in multi-task settings.
Contribution
GATE introduces a novel graph-based adaptive approach for evolving reusable tools across multiple tasks, addressing limitations of single-task frameworks.
Findings
Achieves up to 4.3x faster milestone completion in Minecraft.
Improves code generation accuracy by 9.23%.
Enhances agent task performance by 10.03%.
Abstract
Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-task settings. To address these challenges, we propose GATE (Graph-based Adaptive Tool Evolution), an adaptive framework that dynamically constructs and evolves a hierarchical graph of reusable tools across multiple scenarios. We evaluate GATE on open-ended tasks (Minecraft), agent-based tasks (TextCraft, DABench), and code generation tasks (MATH, Date, TabMWP). Our results show that GATE achieves up to 4.3x faster milestone completion in Minecraft compared to the previous SOTA, and provides an average improvement of 9.23% over existing tool-making methods in code generation tasks and 10.03% in agent tasks. GATE demonstrates the power of adaptive evolution, balancing tool quantity, complexity, and functionality…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReinforcement Learning in Robotics · Evolutionary Algorithms and Applications · Artificial Intelligence in Games
