# AgriAgent: Contract-Driven Planning and Capability-Aware Tool Orchestration in Real-World Agriculture

Source: [AgriAgent: Contract-Driven Planning and Capability-Aware Tool Orchestration in Real-World Agriculture](<https://www.sota2.com/research/paper/696722f6e25ad2fa9d1ec032>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-15T05:00:04.561Z

Authors: Bo Yang, Yu Zhang, Yunkui Chen, Lanfei Feng, Xiao Xu, Nueraili Aierken, Shijian Li

Published: 2026-01-13T07:53:09.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Agricultural Agent Planning and Execution on AgriAgent Full set](<https://www.sota2.com/research/sota/agricultural-agent-planning-and-execution-on-agriagent-full-set.md>): Agricultural Agent Planning and Execution; AgriAgent Full set; Coverage: 100.

- [Agricultural Agent Planning and Execution on AgriAgent Non-Zero](<https://www.sota2.com/research/sota/agricultural-agent-planning-and-execution-on-agriagent-non-zero.md>): Agricultural Agent Planning and Execution; AgriAgent Non-Zero; Task Fulfillment: 87.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.08308>)

[PDF](<https://arxiv.org/pdf/2601.08308.pdf>)