Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents
LLM agents increasingly act as autonomous merchants that write their own product listings, and under competitive pressure, they fabricate attributes to win sales. Even under instructions to be honest, they fabricate attributes in a majority of listings across models. A platform's obvious remedy---verifying each claim against the truth---is unavailable, because it observes only a noisy, biased complaint signal, never the ground truth. We design CARP, a reputation-penalty mechanism with a deadband
Record details
Published: 30 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Bias & fairness · Agents & autonomy
Retrieved: 31 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.
Inference-Time Policy Alignment for Fair Reinforcement Learning
arXiv fairness query · 31 July 2026
Parameterized Fair Resource Allocation under Diversity Constraints
arXiv fairness query · 29 July 2026
Learning faults in time: sequential behavioural modelling for complex fault detection in multi-robot systems
Frontiers in Robotics and AI · 29 July 2026
Private Again: AI Agents Restore Anonymity---Foreclosing Discrimination and Its Proof
arXiv cs.CY · 28 July 2026
Douyin Multimodal Embedding Model Technical Report
HuggingFace Daily Papers · 2 August 2026
Heterogeneous Multi-Agent Reinforcement Learning for Radio Resource Management under Coupled Finite-Horizon Constraints
arXiv fairness query · 3 August 2026
How to cite this record
ethics.ai (30 July 2026), “Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents,” evidence record 15228, https://ethics.ai/record/15228 (originally published by arXiv cs.AI).
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.