Technical Limitations of LLM-Based AI Agents and Their Links to Bias and Governance Challenges: A Narrative Review

Технические ограничения ИИ-агентов на основе больших языковых моделей и их связь с проблемами предвзятости и управления: нарративный обзор
Jungyub Woo, Sewoong Lee, Sangsu Choi
2026-09-28

AI governanceLLM-based AI agentsbias propagationmulti-agent collaborationtool calling
Large language model (LLM)-based AI agents combine reasoning and planning, memory, external knowledge use, tool calling, and multi-agent collaboration to perform complex tasks. However, they face planning failures, context-maintenance limitations, collaboration instability, vulnerabilities arising from external interactions, bias, unclear attribution of responsibility, and difficulties in oversight and incident tracing. This narrative literature review examined the technological evolution and technical limitations of AI agents and developed a conceptual mapping relating these limitations to selected issues of bias and governance. Selected early theoretical studies were included; the main focus was post-2022 scholarly literature and official institutional and corporate materials through July 2026, with publication-status and evidence updates during revision in September 2026. Sources were categorized into concepts and trends, single- and multi-agent architectures, technical limitations, and socio-ethical issues; limitations were compared using a problem addressed–mitigation approach–residual limitation framework. The analysis suggests that autonomous actions performed on behalf of users, ambiguity in the scope of authority, multi-agent interactions, external knowledge use, observation of external environments, and tool calling may be linked to unclear attribution of responsibility, bias propagation and amplification, and difficulties in oversight and incident tracing. Potential mediators include multiple actors, miscoordination and conformity, inherited external-source biases, and new attack surfaces. This conceptual mapping provides a basis for future research on trustworthy AI-agent design, operation, and governance.
1
LLM-based AI agents face planning failures, context-maintenance limitations, unstable collaboration, external-interaction vulnerabilities, and oversight difficulties.
2
Potential mediators include multiple actors, miscoordination, conformity, inherited biases from external sources, and newly introduced attack surfaces.
3
The conceptual mapping establishes a basis for future research on trustworthy AI-agent design, operation, and governance.
4
The review maps autonomous actions, ambiguous authority, multi-agent interactions, external knowledge use, environmental observation, and tool calling to governance and bias challenges.
5
These technical features may contribute to unclear responsibility attribution, bias propagation and amplification, and difficulties in oversight and incident tracing.

LLM-based AI agents

Their technical limitations and their links to bias propagation, responsibility attribution, oversight, and incident tracing

Publication Details
Publication Date
2026-09-28
Journal
Publisher
ISSN
Cited by
0
Access Type
Author Information
Authors
Jungyub Woo
Sewoong Lee
Sangsu Choi
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%