SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows

TL;DR

SHIELDA is a modular framework that improves exception handling in LLM-driven workflows by classifying exceptions, linking them to root causes, and enabling structured, phase-aware recovery strategies.

Contribution

The paper introduces SHIELDA, a novel structured exception handling framework for LLM agentic workflows, with a comprehensive taxonomy and a modular recovery approach.

Findings

Effective cross-phase recovery demonstrated on AutoPR agent

Structured handling improves robustness of LLM workflows

Exception classification enhances root cause analysis

Abstract

Large Language Model (LLM) agentic systems are software systems powered by LLMs that autonomously reason, plan, and execute multi-step workflows to achieve human goals, rather than merely executing predefined steps. During execution, these workflows frequently encounter exceptions. Existing exception handling solutions often treat exceptions superficially, failing to trace execution-phase exceptions to their reasoning-phase root causes. Furthermore, their recovery logic is brittle, lacking structured escalation pathways when initial attempts fail. To tackle these challenges, we first present a comprehensive taxonomy of 36 exception types across 12 agent artifacts. Building on this, we propose SHIELDA (Structured Handling of Exceptions in LLM-Driven Agentic Workflows), a modular runtime exception handling framework for LLM agentic workflows. SHIELDA uses an exception classifier to select a predefined exception handling pattern from a handling pattern registry. These patterns are then executed via a structured handling executor, comprising local handling, flow control, and state recovery, to enable phase-aware recovery by linking exceptions to their root causes and facilitating composable strategies. We validate SHIELDA's effectiveness through a case study on the AutoPR agent, demonstrating effective, cross-phase recovery from a reasoning-induced exception.