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

Cong Cao; Jingyao Zhang; Kun Tong

cs.AIMar 9, 2026

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

Authors: Cong Cao, Jingyao Zhang, Kun Tong

Organizations: Independent Researcher, Hangzhou, Zhejiang, China · Beihang University, Hangzhou, Zhejiang, China

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.

Figures & tables

Figure 1: A categorization of autonomous robot methods.

Figure 2: Structure of HECG Transition Policy.The agent selects among alternative action strategies by integrating task value, cost, risk, and LLM-based scores, and determines the final action via a softmax policy under partial observability.

Figure 3: LLM Goal Compliance Evaluation Results.

Figure 5: Evaluation Metrics of Task Plan

Policy Variant	TSR	Recovery Steps	Semantic Consistency
Readbook (bedroom_and_kitchen)
Full Policy	0.806	1.62	0.86
w/o Value	0.708	2.02	0.84
w/o Cost	0.729	1.82	0.83
w/o Risk	0.342	2.66	0.80
w/o LLM	0.337	2.95	0.68

Table 3: Ablation results on transition policy components for Readbook, Putdishwasher, and Preparefood tasks.

Policy Variant	TSR	Recovery Steps	Semantic Consistency
Putfridge (bathroom_and_livingroom)
Full Policy	0.736	1.55	0.88
w/o Value	0.494	1.75	0.84
w/o Cost	0.690	2.07	0.86
w/o Risk	0.467	2.39	0.80
w/o LLM	0.418	2.99	0.66

Table 4: Ablation results on transition policy components for Putfridge and Setuptable tasks.

Figure 6: Threshold Sensitivity Analysis & Comprehensive Performance Score By Policy Variant and Model

Policy Variant	Main (%)	Correction (%)	Fallback (%)
Low Error ( $e_{i}\leq\epsilon_{i}$ )
Full Policy	91.8	6.8	1.4
w/o Value	85.0	13.2	1.8
w/o Cost	87.6	11.3	1.1
w/o Risk	76.7	21.7	1.6
w/o LLM	82.1	16.3	1.6

Table 5: Transition type distribution under different error regimes (averaged across models).

Failure Attribution for LLM Agents

See all 29 papers

Jul 15, 2026

Experience Memory Graph: One-Shot Error Correction for Agents

Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations. However, in complex, long-horizon tasks, these agents frequently suffer from compounding errors and struggle to recover from failures. Existing self-correction mechanisms rely on prompt-based reflection, which is inherently brittle, incurs heavy time and API costs due to iterative trial-and-error loops, and produces task-specific memory that may be hard to generalize to new scenarios. To address this, we propose Experience Memory Graph (EMG), a framework that reformulates agent failure recovery as a graph matching problem. At training time, we convert both failed exploration trajectories and successful expert trajectories into directed action decision graphs. By matching these graphs, we extract common subgraphs (successful workflows) and graph edit paths that explicitly indicate how to correct failures (e.g., which actions to add, delete, or relabel under a given observation), and store them in a memory graph with intra-task nodes and cross-task edges. At test time, EMG retrieves relevant insights and guides the agent in a single, loop-free execution. Experiments on ALFWorld and ScienceWorld show that EMG consistently outperforms state-of-the-art reflection baselines in success rate and average reward, while requiring no test-time trial-and-error.

Wenjun Wang, Yuchen Fang, Fengrui Liu +2

University of Electronic Science and Technology of China

Agent Memory LLM Self-Correction Graph-Based Agent Memory Long-Horizon LLM Agents Memory-Augmented Language Model Agents

Ask PDF

Jul 29, 2026

Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems

Large Language Model~(LLM)-based agents have demonstrated exceptional performance across a wide range of complex interactive tasks. However, they often struggle with long-horizon interactive tasks common in domains, such as embodied AI. The complexity and vast action spaces in these settings lead to compounding errors, where a single suboptimal action can derail an entire trajectory, causing the agent to exhaust its limited step budget on inefficient or unrecoverable paths. To overcome this without costly fine-tuning, we draw inspiration from software debugging, where execution logs are analyzed to preemptively catch errors. We propose Trajectory Graph Copilot, a novel framework that acts as a ``copilot'' for LLM agents by diagnosing potential action errors before they are executed. At its core,Graph Debugger models historical trajectories as a probabilistic graph and uses a Graph Neural Network to identify sequential action patterns that frequently lead to failure. Functioning as a proactive diagnostic sandbox, our method provides early warnings on potentially flawed actions, prompting the agent to self-correct. This pre-action error diagnosis prevents costly mistakes, significantly enhancing the agent's ability to complete long-horizon tasks successfully. The extensive experiments on four benchmarks with three LLM agents demonstrate a

14.69\%

pass ratio improvement on average.

Xu Zheng, Zhuomin Chen, Chaohao Lin +4

1Florida International University, Miami, FL, USA · 2Arizona State University, Tempe, AZ, USA · 3NEC Laboratories America, Princeton, NJ, USA +1

Long-Horizon Agent Tasks Long-Horizon LLM Agents LLM Agent Reliability

Ask PDF

Mar 11, 2026

Trajectory-Informed Memory Generation for Self-Improving Agent Systems

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar errors, and miss opportunities to apply successful strategies from past executions. We present a novel framework for automatically extracting actionable learnings from agent execution trajectories and utilizing them to improve future performance through contextual memory retrieval. Our approach comprises four components: (1) a Trajectory Intelligence Extractor that performs semantic analysis of agent reasoning patterns, (2) a Decision Attribution Analyzer that identifies which decisions and reasoning steps led to failures, recoveries, or inefficiencies, (3) a Contextual Learning Generator that produces three types of guidance -- strategy tips from successful patterns, recovery tips from failure handling, and optimization tips from inefficient but successful executions, and (4) an Adaptive Memory Retrieval System that injects relevant learnings into agent prompts based on multi-dimensional similarity. Unlike existing memory systems that store generic conversational facts, our framework understands execution patterns, extracts structured learnings with provenance, and retrieves guidance tailored to specific task contexts. Evaluation on the AppWorld benchmark demonstrates consistent improvements, with up to 14.3 percentage point gains in scenario goal completion on held-out tasks and particularly strong benefits on complex tasks (28.5~pp scenario goal improvement, a 149% relative increase).

Gaodan Fang, Vatche Isahagian, K. R. Jayaram +4

Agents and Automation Lab, IBM Research USA

LLM Agent Self-Improvement LLM Agent Memory Memory-Augmented Language Model Agents

Ask PDF

Abstract

Failure Attribution for LLM Agents

Explore similar work

Experience Memory Graph: One-Shot Error Correction for Agents

Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems

Trajectory-Informed Memory Generation for Self-Improving Agent Systems