Strategic Adaptation Under Contextual Change: Insights from a Dyadic Negotiation Testbed for AI Coaching Technologies

2026-02-04

AI Summary

This study investigates the strategic adaptability of AI negotiation agents in response to contextual perturbations, with a focus on how shifts in external conditions affect cooperation maintenance and relational quality. We introduce a reusable two-party negotiation testbed featuring a controlled perturbation mechanism that dynamically alters one party’s Best Alternative to a Negotiated Agreement (BATNA) mid-dialogue to repeatedly elicit adaptive behaviors. Through six rounds of chat-based experiments, behavioral sequence analysis, and strategy classification (integrative vs. distributive), we find that perturbations significantly suppress transitions from integrative to distributive strategies, reduce strategic diversity, and induce a drift toward distributive negotiation. This drift, independent of objective outcomes, substantially degrades relational experience and is modulated by prior behavioral history. Our work establishes a comparable benchmark and offers theoretical insights for evaluating and improving AI negotiation systems.

Technology Category

• Multiagent Systems: Agreement, Argumentation & Negotiation
• Game Theory and Economic Paradigms: Behavioral Game Theory
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Strategic adaptation -- the ability to adjust interaction behavior in response to changing constraints and leverage -- is a central goal of negotiation training and an emerging target for AI coaching systems. However, adaptation is difficult to evaluate because adaptation-relevant moments arise unpredictably in typical tasks. We study a reusable dyadic negotiation testbed that employs a controlled midstream change in one party's outside alternative as a repeatable perturbation to stress-test adaptation. In a six-round chat-based negotiation study (N=100), the perturbation reliably reorganized interaction dynamics: transitions between integrative (cooperative) and distributive (positional) behaviors declined, behavioral diversity narrowed, and interactions drifted toward more distributive tactics. Critically, this distributive drift predicted worse relational experience net of objective outcomes, and adaptation patterns were path dependent on prior behavior. These results establish a methodological bridge for evaluating and comparing AI coaching systems on strategic adaptation as a process and identify failure modes and design targets for adaptive interaction support.

Problem

• strategic adaptation
• AI coaching
• dyadic negotiation
• contextual change
• distributive drift

Innovation

• strategic adaptation
• dyadic negotiation testbed
• controlled perturbation
• AI coaching
• behavioral dynamics