A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation

2026-03-09

AI Summary

This work addresses the low reliability of autonomous agents in complex multi-step tasks, which stems from negative policy transfer, ambiguous error attribution, and insufficient contextual utilization. To mitigate these issues, the authors propose a hierarchical error-correction graph framework that integrates multidimensional transferable strategies (MDTS) to align semantic intent with performance outcomes, constructs a ten-category error matrix (EMC) for precise failure attribution, and introduces a causal context graph (CCGR) enabling structured retrieval beyond vector similarity. By synergistically combining large language model reasoning, multidimensional evaluation metrics, an error typology, and causal subgraph retrieval, the framework significantly reduces the risk of negative policy transfer, enhances root-cause analysis accuracy, accelerates policy adaptation, and ultimately improves execution reliability in dynamic environments.

Technology Category

• Multiagent Systems: Adversarial Agents
• Reasoning under Uncertainty: Sequential Decision Making
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We propose a Hierarchical Error-Corrective Graph FrameworkforAutonomousAgentswithLLM-BasedActionGeneration(HECG),whichincorporates three core innovations: (1) Multi-Dimensional Transferable Strategy (MDTS): by integrating task quality metrics (Q), confidence/cost metrics (C), reward metrics (R), and LLM-based semantic reasoning scores (LLM-Score), MDTS achieves multi-dimensional alignment between quantitative performance and semantic context, enabling more precise selection of high-quality candidate strate gies and effectively reducing the risk of negative transfer. (2) Error Matrix Classification (EMC): unlike simple confusion matrices or overall performance metrics, EMC provides structured attribution of task failures by categorizing errors into ten types, such as Strategy Errors (Strategy Whe) and Script Parsing Errors (Script-Parsing-Error), and decomposing them according to severity, typical actions, error descriptions, and recoverability. This allows precise analysis of the root causes of task failures, offering clear guidance for subsequent error correction and strategy optimization rather than relying solely on overall success rates or single performance metrics. (3) Causal-Context Graph Retrieval (CCGR): to enhance agent retrieval capabilities in dynamic task environments, we construct graphs from historical states, actions, and event sequences, where nodes store executed actions, next-step actions, execution states, transferable strategies, and other relevant information, and edges represent causal dependencies such as preconditions for transitions between nodes. CCGR identifies subgraphs most relevant to the current task context, effectively capturing structural relationships beyond vector similarity, allowing agents to fully leverage contextual information, accelerate strategy adaptation, and improve execution reliability in complex, multi-step tasks.

Problem

• Autonomous Agents
• LLM-Based Action Generation
• Error Correction
• Strategy Transfer
• Task Failure Analysis

Innovation

• Multi-Dimensional Transferable Strategy
• Error Matrix Classification
• Causal-Context Graph Retrieval
• LLM-Based Action Generation
• Hierarchical Error-Corrective Framework