FARM: Field-Aware Resolution Model for Intelligent Trigger-Action Automation

TL;DR

FARM is a novel two-stage model that automates the generation of executable trigger-action applets by accurately binding trigger outputs to action inputs, significantly improving configuration accuracy.

Contribution

The paper introduces FARM, a two-stage architecture combining contrastive encoding and LLM-based multi-agent selection to fully automate trigger-action applet configuration.

Findings

Achieves 81% joint accuracy at the function level.

Outperforms baseline TARGE by 23 percentage points.

Generates executable applets with correct ingredient-to-field bindings.

Abstract

Trigger-Action Programming (TAP) platforms such as IFTTT and Zapier enable Web of Things (WoT) automation by composing event-driven rules across heterogeneous services. A TAP applet links a trigger to an action and must bind trigger outputs (ingredients) to action inputs (fields) to be executable. Prior work largely treats TAP as service-level prediction from natural language, which often yields non-executable applets that still require manual configuration. We study the function-level configuration problem: generating complete applets with correct ingredient-to-field bindings. We propose FARM (Field-Aware Resolution Model), a two-stage architecture for automated applet generation with full configuration. Stage 1 trains contrastive dual encoders with selective layer freezing over schema-enriched representations, retrieving candidates from 1,724 trigger functions and 1,287 action functions (2.2M possible trigger-action pairs). Stage 2 performs selection and configuration using an LLM-based multi-agent pipeline. It includes intent analysis, trigger selection, action selection via cross-schema scoring, and configuration verification. Agents coordinate through shared state and agreement-based selection. FARM achieves 81% joint accuracy on Gold (62% Noisy, 70% One-shot) at the function level, where both trigger and action functions must match the ground truth. For comparison with service-level baselines, we map functions to their parent services and evaluate at the service level. FARM reaches 81% joint accuracy and improves over TARGE by 23 percentage points. FARM also generates ingredient-to-field bindings, producing executable automation configurations.