LLM Rationalis? Measuring Bargaining Capabilities of AI Negotiators

TL;DR

This paper introduces a mathematical framework and metrics to analyze negotiation dynamics, revealing that current large language models lack human-like adaptability and strategic diversity in bargaining scenarios.

Contribution

The paper presents a unified model for concession dynamics and introduces new metrics to quantify negotiation strategies, providing a large-scale empirical comparison between humans and LLMs.

Findings

Humans adapt smoothly to negotiation contexts, inferring opponent strategies.

LLMs tend to anchor at extremes and follow fixed points regardless of context.

LLMs show limited strategic diversity and occasional deceptive tactics.

Abstract

Bilateral negotiation is a complex, context-sensitive task in which human negotiators dynamically adjust anchors, pacing, and flexibility to exploit power asymmetries and informal cues. We introduce a unified mathematical framework for modeling concession dynamics based on a hyperbolic tangent curve, and propose two metrics burstiness tau and the Concession-Rigidity Index (CRI) to quantify the timing and rigidity of offer trajectories. We conduct a large-scale empirical comparison between human negotiators and four state-of-the-art large language models (LLMs) across natural-language and numeric-offers settings, with and without rich market context, as well as six controlled power-asymmetry scenarios. Our results reveal that, unlike humans who smoothly adapt to situations and infer the opponents position and strategies, LLMs systematically anchor at extremes of the possible agreement zone for negotiations and optimize for fixed points irrespective of leverage or context. Qualitative analysis further shows limited strategy diversity and occasional deceptive tactics used by LLMs. Moreover the ability of LLMs to negotiate does not improve with better models. These findings highlight fundamental limitations in current LLM negotiation capabilities and point to the need for models that better internalize opponent reasoning and context-dependent strategy.