Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent Failure
Large language model agents demonstrate expert-level reasoning, yet consistently fail on enterprise-specific tasks due to missing domain knowledge -- terminology, operational procedures, system interdependencies, and institutional decisions that exist largely as tribal knowledge. Current approaches fall into two categories: top-down knowledge engineering, which documents domain knowledge before agents use it, and bottom-up automation, where agents learn from task experience. Both have fundamenta
Record details
Published: 14 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.
Semantic Consensus: Process-Aware Conflict Detection and Resolution for Enterprise Multi-Agent LLM Systems
arXiv · 13 March 2026
HR-Agents: Using Multiple LLM-based Agents to Improve Q&A about Brazilian Labor Legislation
arXiv · 13 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
MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment
arXiv · 18 March 2026
How to cite this record
ethics.ai (14 March 2026), “Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent Failure,” evidence record 7239, https://ethics.ai/record/7239 (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.