Abstract
The hidden profile paradigm is a foundational tool of CSCW research on computer-mediated group decision making: a group can identify the collectively optimal option only if its members surface their uniquely held information, and asynchronous communication is known to improve that pooling in human groups. As multi-agent LLM systems take on group decision-support roles, it is unclear whether the same channel-level interventions improve their performance. We replicate the hidden profile paradigm with groups of three LLM agents from four families (Kimi K2, GPT-OSS 120B, Gemini 2.5 Flash, Llama 4 Scout 17B) in a two-by-two design crossing communication mode (synchronous, asynchronous) with information distribution (shared, hidden). Across 219 valid sessions, only one model-by-mode cell exceeds the three-candidate chance baseline of 33 percent: Kimi K2 under asynchronous communication, at 87 percent correct (Fisher's exact, two-sided p equals 0.002), an early-stage result from 15 sessions that awaits larger-n replication; two other models share private information at rates above 75 percent but never aggregate it into the correct decision. In this task and these model families, information sharing and information integration appear to be dissociated capabilities, and we develop the implications for CSCW systems that scaffold AI-mediated distributed decision making.
Cite this work
Carlos Toxtli-Hernández and Manuel Delaflor. 2026. Hidden Profile Decision Making in Multi-Agent LLM Groups. Companion of the Computer-Supported Cooperative Work and Social Computing (CSCW Companion ’26). https://doi.org/10.1145/3785651.3831525
@inproceedings{Toxtli2026Hidden,
title = {Hidden Profile Decision Making in Multi-Agent LLM Groups},
author = {Carlos Toxtli and Manuel Delaflor},
booktitle = {Companion of the Computer-Supported Cooperative Work and Social Computing (CSCW Companion ’26)},
year = {2026},
doi = {10.1145/3785651.3831525}
}
