Chapter 6 · 2026
Architecting Trust in Artificial Epistemic Agents
Nahema Marchal, Stephanie Chan, Matija Franklin
Abstract
Large language models are increasingly acting as epistemic agents, influencing our knowledge environment and decision-making. This paper argues that the impact of these AI agents on knowledge creation and synthesis necessitates a fundamental shift in evaluation and governance, particularly concerning their reliability and calibration to human norms. The authors propose a framework for building trustworthy epistemic AI agents, emphasizing epistemic competence, falsifiability, and virtuous behaviors to ensure a beneficial human-AI knowledge ecosystem.
Topics
AI agentstrust calibrationepistemic agentsknowledge ecosystemAI governance
Relevance Scores
Long-Horizon Score85
Enterprise Score80
Completeness75
Paper Info
Year2026
Venue
Type
ChapterCh. 6
Authors3
Zone III Analysis
Related Papers
ReAct: Synergizing Reasoning and Acting in Language Mod…
2023 · Ch.1
Reflexion: Language Agents with Verbal Reinforcement Le…
2023 · Ch.1
Tree of Thoughts: Deliberate Problem Solving with Large…
2023 · Ch.1
Toolformer: Language Models Can Teach Themselves to Use…
2023 · Ch.1
View all Chapter 6 papers →