Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support
This addresses the problem of ineffective human-AI collaboration in expert decision support, proposing a foundational shift rather than incremental improvements.
The paper tackles the problem that human-AI teams in high-stakes decision-making do not reliably outperform individuals, attributing this to a mismatch where current agents act as answer engines rather than collaborative partners in sensemaking. It proposes Collaborative Causal Sensemaking (CCS) as a research agenda to develop agents that co-construct causal explanations and adapt goals, aiming to close this complementarity gap.
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. These directions can advance MAS research toward agents that think with their human partners rather than for them.