Semantic Consensus: Process-Aware Conflict Detection and Resolution for Enterprise Multi-Agent LLM Systems
Multi-agent large language model (LLM) systems are rapidly emerging as the dominant architecture for enterprise AI automation, yet production deployments exhibit failure rates between 41% and 86.7%, with nearly 79% of failures originating from specification and coordination issues rather than model capability limitations. This paper identifies Semantic Intent Divergence--the phenomenon whereby cooperating LLM agents develop inconsistent interpretations of shared objectives due to siloed context
Record details
Published: 13 March 2026
Source: arXiv
Category: Research
Topics: Jobs & economy · Agents & autonomy
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Governing the Agentic Enterprise: A Governance Maturity Model for Managing AI Agent Sprawl in Business Operations
arXiv · 13 March 2026
HR-Agents: Using Multiple LLM-based Agents to Improve Q&A about Brazilian Labor Legislation
arXiv · 13 March 2026
Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent Failure
arXiv · 14 March 2026
Agentic AI for Embodied-enhanced Beam Prediction in Low-Altitude Economy Networks
arXiv · 12 March 2026
CentaurTA Studio: A Self-Improving Human-Agent Collaboration System for Thematic Analysis
arXiv · 18 March 2026
Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)
arXiv · 18 March 2026
How to cite this record
ethics.ai (13 March 2026), “Semantic Consensus: Process-Aware Conflict Detection and Resolution for Enterprise Multi-Agent LLM Systems,” evidence record 7273, https://ethics.ai/record/7273 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.