AgriAgent: Contract-Driven Planning and Capability-Aware Tool Orchestration in Real-World Agriculture
This addresses the problem of inefficient task execution in agricultural AI systems, offering a domain-specific solution that is incremental in improving agent frameworks.
The paper tackles the challenge of handling diverse tasks with varying complexity and incomplete tool availability in real-world agricultural agent systems by proposing AgriAgent, a two-level framework that uses contract-driven planning and capability-aware tool orchestration, achieving higher execution success rates and robustness on complex tasks compared to existing baselines.
Intelligent agent systems in real-world agricultural scenarios must handle diverse tasks under multimodal inputs, ranging from lightweight information understanding to complex multi-step execution. However, most existing approaches rely on a unified execution paradigm, which struggles to accommodate large variations in task complexity and incomplete tool availability commonly observed in agricultural environments. To address this challenge, we propose AgriAgent, a two-level agent framework for real-world agriculture. AgriAgent adopts a hierarchical execution strategy based on task complexity: simple tasks are handled through direct reasoning by modality-specific agents, while complex tasks trigger a contract-driven planning mechanism that formulates tasks as capability requirements and performs capability-aware tool orchestration and dynamic tool generation, enabling multi-step and verifiable execution with failure recovery. Experimental results show that AgriAgent achieves higher execution success rates and robustness on complex tasks compared to existing tool-centric agent baselines that rely on unified execution paradigms. All code, data will be released at after our work be accepted to promote reproducible research.