Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support

TL;DR

This paper advocates for developing AI agents capable of collaborative causal sensemaking to improve human-AI decision support, addressing the current mismatch where AI acts as answer engines rather than partners.

Contribution

It introduces the concept of Collaborative Causal Sensemaking (CCS) and outlines a research agenda for training, representation, and evaluation to foster AI-human teamwork.

Findings

Current AI agents are answer engines, not collaborative partners.

Proposes new training environments that reward collaborative thinking.

Emphasizes shared mental models and trust-centered evaluation.

Abstract

LLM-based agents are increasingly deployed for expert decision support, yet human-AI teams in high-stakes settings do not yet reliably outperform the best individual. We argue this complementarity gap reflects a fundamental mismatch: current agents are trained as answer engines, not as partners in the collaborative sensemaking through which experts actually make decisions. Sensemaking (the ability to co-construct causal explanations, surface uncertainties, and adapt goals) is the key capability that current training pipelines do not explicitly develop or evaluate. We propose Collaborative Causal Sensemaking (CCS) as a research agenda to develop this capability from the ground up, spanning new training environments that reward collaborative thinking, representations for shared human-AI mental models, and evaluation centred on trust and complementarity. Taken together, these directions shift MAS research from building oracle-like answer engines to cultivating AI teammates that co-reason with their human partners over the causal structure of shared decisions, advancing the design of effective human-AI teams.