{"ID":2831803,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.07801","arxiv_id":"2512.07801","title":"Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support","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.","short_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 sen...","url_abs":"https://arxiv.org/abs/2512.07801","url_pdf":"https://arxiv.org/pdf/2512.07801v5","authors":"[\"Raunak Jain\"]","published":"2025-12-08T18:30:41Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.HC\",\"cs.LG\"]","methods":"[\"Large Language Model\"]","has_code":false}