PrefBench: Evaluating Zero-Shot LLM Agents in Hidden-Preference Personalized Pricing Negotiations

arXiv cs.AI Papers

Summary

PrefBench is a new benchmark designed to evaluate zero-shot LLM agents in personalized pricing negotiations with hidden preferences, assessing their ability to infer and adapt to user preferences in a negotiation setting.

arXiv:2605.22855v1 Announce Type: cross Abstract: Personalized pricing negotiations are a challenging testbed for LLM agents because successful interaction does not guarantee profitable decision making. A seller may produce valid actions and close many deals while still pricing poorly when buyer willingness to pay and bargaining traits remain hidden. This paper presents PrefBench, a simulator-based benchmark for hidden-preference personalized pricing negotiations. Each episode pairs a simulated buyer with a fixed vehicle-customization bundle; the seller observes public persona descriptors, bundle information, and negotiation history, while latent buyer variables govern valuation, patience, counter-offer behavior, and walkaway decisions. PrefBench evaluates this setting through an LLM-facing state-summary protocol that constrains agents to return strict JSON actions under a fixed hidden-information boundary. We evaluate zero-shot LLM sellers against heuristic references over 7,500 episodes. The tested LLMs follow the protocol reliably and achieve deal rates above 0.99, but their seller-profit outcomes remain weak: the best LLM average profit is only slightly above the random baseline and far below a simple concession heuristic under the same episode stream. These results show that structured action compliance and agreement-seeking behavior can coexist with weak profit-sensitive bargaining. PrefBench provides a controlled benchmark for evaluating pricing-agent behavior under hidden buyer preferences.
Original Article
View Cached Full Text

Cached at: 05/25/26, 09:01 AM

# PrefBench: Evaluating Zero-Shot LLM Agents in Hidden-Preference Personalized Pricing Negotiations
Source: [https://arxiv.org/abs/2605.22855](https://arxiv.org/abs/2605.22855)
Bibliographic Tools

## Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Code, Data, Media

## Code, Data and Media Associated with this Article

Demos

## Demos

Related Papers

## Recommenders and Search Tools

About arXivLabs

## arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website\.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy\. arXiv is committed to these values and only works with partners that adhere to them\.

Have an idea for a project that will add value for arXiv's community?[**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html)\.

Similar Articles

POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents

arXiv cs.AI

POLAR-Bench is a diagnostic benchmark that evaluates the privacy-utility trade-off in LLM agents by testing their ability to follow privacy policies while being adversarially probed by third-party models. Results show frontier models protect over 99% of protected attributes but smaller open-weight models leak over half, highlighting gaps in intent-following.

Preference Estimation via Opponent Modeling in Multi-Agent Negotiation

arXiv cs.CL

This paper proposes a novel preference estimation method that integrates natural language information from LLMs into a structured Bayesian opponent modeling framework for multi-agent negotiation. The approach leverages LLMs to extract qualitative cues from utterances and convert them into probabilistic formats, demonstrating improved agreement rates and preference estimation accuracy on multi-party negotiation benchmarks.