HTAA: Enhancing LLM Planning via Hybrid Toolset Agentization & Adaptation

2026-04-12

AI Summary

This work addresses the inefficiency, error propagation, and limited scalability of large language models when orchestrating numerous tools. To overcome these challenges, the authors propose the Hierarchical Tool-Agent Architecture (HTAA), which encapsulates frequently used tool combinations into dedicated agent-based tools, thereby constructing a hierarchical planning framework. HTAA further incorporates a trajectory-based asymmetric planner with an adaptive training mechanism featuring backward reconstruction and forward refinement. This approach effectively compresses the action space and minimizes redundant tool invocations. Experimental results on the InfoVerify dataset and standard benchmarks demonstrate that HTAA significantly improves task success rates, shortens tool invocation trajectories, reduces context overhead, and substantially lowers human verification costs in real-world deployment scenarios.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Multiagent Planning

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficiency and error accumulation inherent in flat tool-calling architectures. To address this, we propose Hybrid Toolset Agentization & Adaptation (HTAA), a hierarchical framework for scalable tool-use planning. We propose a novel toolset agentization paradigm, which encapsulates frequently co-used tools into specialized agent tools, thereby reducing the planner's action space and mitigating redundancy. To ensure effective coordination, we design Asymmetric Planner Adaptation, a trajectory-based training paradigm that aligns the high-level planner with agent tools via backward reconstruction and forward refinement. To validate the performance of HTAA, we conduct experiments on a real-world internal dataset, InfoVerify, based on the POI validation workflow of China's largest online large-scale ride-hailing platform, featuring long-horizon executable tool trajectories. Experiments on InfoVerify and widely-used benchmarks show that HTAA consistently achieves higher task success rates, requires short tool calling trajectories, and significantly reduces context overhead compared to strong baselines. Furthermore, in a production deployment, HTAA substantially reduces manual validation effort and operational cost, demonstrating its practical efficacy.

Problem

• tool-use planning
• scalable tool integration
• large language models
• error accumulation
• action space reduction

Innovation

• toolset agentization
• hierarchical planning
• asymmetric planner adaptation
• trajectory-based training
• scalable tool use