What question did this study set out to answer?

To develop and evaluate an integrated self-healing framework that detects failures, assesses reliability, and automates recovery in LLM-based autonomous software agents.

August 15, 2026International Journal of Software Engineering and Knowledge Engineering

An Integrated Self-Healing Framework for Enhancing the Reliability of LLM-Based Autonomous Software Agents

View Full Paper

Ask AI

Bookmark

Authors

CJC. JeongSamsung (South Korea)YSYounggun Shin

Discussion

Member takes

Implication

Framework evaluation demonstrates improved task success rates and reduced fault propagation in LLM-based autonomous software agents, indicating a pathway toward robust AI self-healing systems.

Key Points

To develop and evaluate an integrated self-healing framework that detects failures, assesses reliability, and automates recovery in LLM-based autonomous software agents.
Designed a failure classification taxonomy alongside a quantitative reliability assessment model.
Implemented abnormal behavior detection based on execution patterns and output consistency, combined with recovery via adaptive replanning and prompt correction.
Evaluated system performance within a simulated multi-agent workflow environment executing real-world operational task scenarios.
Demonstrated significant increases in task success rates and reduced fault propagation across agent workflows compared to existing baselines.
Achieved improved overall robustness by monitoring both internal reasoning processes and external execution outcomes.

Cite This Study

Jeong et al. (2026) studied this question.

synapsesocial.com/papers/6a8019bb75c2e31742c85e5e https://doi.org/10.1142/s0218194026500695

View Full Paper

Ask AI

Bookmark

August 15, 2026International Journal of Software Engineering and Knowledge Engineering

An Integrated Self-Healing Framework for Enhancing the Reliability of LLM-Based Autonomous Software Agents

View Full Paper

Ask AI

Bookmark

Authors

CJC. JeongSamsung (South Korea)YSYounggun Shin

Discussion

Member takes

Implication

Framework evaluation demonstrates improved task success rates and reduced fault propagation in LLM-based autonomous software agents, indicating a pathway toward robust AI self-healing systems.

Key Points

To develop and evaluate an integrated self-healing framework that detects failures, assesses reliability, and automates recovery in LLM-based autonomous software agents.
Designed a failure classification taxonomy alongside a quantitative reliability assessment model.
Implemented abnormal behavior detection based on execution patterns and output consistency, combined with recovery via adaptive replanning and prompt correction.
Evaluated system performance within a simulated multi-agent workflow environment executing real-world operational task scenarios.
Demonstrated significant increases in task success rates and reduced fault propagation across agent workflows compared to existing baselines.
Achieved improved overall robustness by monitoring both internal reasoning processes and external execution outcomes.

Cite This Study

Jeong et al. (2026) studied this question.

synapsesocial.com/papers/6a8019bb75c2e31742c85e5e https://doi.org/10.1142/s0218194026500695

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark