Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Mobasshira Akter Urmi, Raiyan Abdul Baten

TL;DR

This paper tackles the challenge of evaluating strategic adaptation under dynamic context by introducing a reusable dyadic negotiation testbed with a controlled midstream perturbation to outside options. Using a six-round chat-based HR–candidate negotiation, it shows that a turning point disrupts interaction trajectories, reducing behavioral diversity and shifting toward distributive tactics. Crucially, distributive drift predicts worse subjective experience beyond objective outcomes, and adaptation exhibits path dependence on pre-change behavior, highlighting the need for state-aware coaching. The work provides a concrete methodological bridge for evaluating AI coaching systems on adaptation as a process and outlines design targets to support adaptive interaction in dynamic contexts.

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.

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

TL;DR

This paper tackles the challenge of evaluating strategic adaptation under dynamic context by introducing a reusable dyadic negotiation testbed with a controlled midstream perturbation to outside options. Using a six-round chat-based HR–candidate negotiation, it shows that a turning point disrupts interaction trajectories, reducing behavioral diversity and shifting toward distributive tactics. Crucially, distributive drift predicts worse subjective experience beyond objective outcomes, and adaptation exhibits path dependence on pre-change behavior, highlighting the need for state-aware coaching. The work provides a concrete methodological bridge for evaluating AI coaching systems on adaptation as a process and outlines design targets to support adaptive interaction in dynamic contexts.

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.
Paper Structure (16 sections, 1 figure, 4 tables)

This paper contains 16 sections, 1 figure, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methods
  4. Testbed design rationale and payoff construction
  5. Participants and procedure
  6. Measures
  7. Findings
  8. The turning point reliably reorganizes behavior toward distributive tactics
  9. Distributive drift predicts worse experience beyond outcomes
  10. Adaptation is path dependent on pre-turning-point behavior
  11. Discussion and Conclusion
  12. Design implications for interactive training and AI coaching for adaptive contexts
  13. Limitations and future work
  14. Supplementary Materials
  15. Demographic information
  16. ...and 1 more sections

Figures (1)

  • Figure 1: Throughline from adaptation testbed requirements to design choices, observable signals, and AI coaching implications.