Anchor-and-Resume Concession Under Dynamic Pricing for LLM-Augmented Freight Negotiation

TL;DR

This paper introduces a dynamic, monotonic concession framework for freight negotiations that adapts to pricing updates using a deterministic formula, reducing reliance on expensive LLM reasoning.

Contribution

It proposes a two-index anchor-and-resume method that ensures monotonic offers and adapts concession behavior based on load margin structures, improving scalability and transparency.

Findings

Adaptive $eta$ tailors concessions to different spread regimes.

Achieves broker savings comparable to fixed-$eta$ baselines.

Maintains high agreement rates against stochastic LLM carriers.

Abstract

Freight brokerages negotiate thousands of carrier rates daily under dynamic pricing conditions where models frequently revise targets mid-conversation. Classical time-dependent concession frameworks use a fixed shape parameter $\beta$ that cannot adapt to these updates. Deriving $\beta$ from the live spread enables adaptation but introduces a new problem: a pricing shift can cause the formula to retract a previous offer, violating monotonicity. LLM-powered brokers offer flexibility but require expensive reasoning models, produce non-deterministic pricing, and remain vulnerable to prompt injection. We propose a two-index anchor-and-resume framework that addresses both limitations. A spread-derived $\beta$ maps each load's margin structure to the correct concession posture, while the anchor-and-resume mechanism guarantees monotonically non-decreasing offers under arbitrary pricing shifts. All pricing decisions remain in a deterministic formula; the LLM, when used, serves only as a natural-language translation layer. Empirical evaluation across 115,125 negotiations shows that the adaptive $\beta$ tailors behavior by regime: in narrow spreads, it concedes quickly to prioritize deal closure and load coverage; in medium and wide spreads, it matches or exceeds the best fixed-$\beta$ baselines in broker savings. Against an unconstrained 20-billion-parameter LLM broker, it achieves similar agreement rates and savings. Against LLM-powered carriers as more realistic stochastic counterparties, it maintains comparable savings and higher agreement rates than against rule-based opponents. By decoupling the LLM from pricing logic, the framework scales horizontally to thousands of concurrent negotiations with negligible inference cost and transparent decision-making.