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

2026-01-22

AI Summary

This work addresses the common failure of existing trigger-action programming (TAP) automation methods to generate executable rules due to neglecting field-level bindings. It formulates TAP for the first time as a function-level, field-aware binding problem and proposes a two-stage architecture: the first stage retrieves candidate function pairs via a contrastive learning-based dual-encoder, while the second stage employs a multi-agent LLM collaboration mechanism that integrates intent analysis, cross-modal selection, and field binding validation to produce end-to-end executable rules. The approach incorporates schema-enhanced representations, selective layer freezing, and a shared-state consensus mechanism, achieving an 81% function-level joint accuracy on the Gold dataset and improving service-level accuracy by 23 percentage points over the TARGE baseline, substantially advancing the generation of executable automation configurations.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Knowledge Representation and Reasoning: Action, Change, and Causality
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

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

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.

Problem

• Trigger-Action Programming
• Field Binding
• Executable Automation
• Function-level Configuration
• Web of Things

Innovation

• Field-Aware Resolution Model
• Trigger-Action Programming
• Function-level Configuration
• Multi-agent LLM Pipeline
• Executable Automation