AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

When Proxy Agents Disagree, Do Humans Mirror? Manipulating Human Behavior in Moral Dilemmas Through Agents

Haotian Deng, Sitian Wang, Ruxin Wang, Chen Wei, Quanying Liu

AAAI 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Theory-of-mind social reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune individually on each participant's data (IndivNet vs GroupNet)BERT GroupNet · IndivDataaccuracy: 60.2% -> 63.4%Improved
fine-tune individually on each participant's dataBERT GroupNet · GroupDataaccuracy: 59.5% -> 59.6%No clear effect
individual fine-tuningBERT GroupNet · human uncertainty alignmentSpearman correlation: 0.01 -> 0.13Improved
individual fine-tuningBERT GroupNet · low and medium uncertainty dilemmasaccuracyHurt
individual fine-tuningBERT GroupNet · high uncertainty dilemmasaccuracyImproved
select stimuli with fine-tuned individual agents instead of zero-shot modelstimulus selection · human intervention experimentguidance outcome: 6% average improvementImproved
select stimuli with fine-tuned individual agents instead of zero-shot modelstimulus selection · human intervention experimenttarget ratio: 29% improvementImproved
higher human uncertainty leveldilemma groups · BJSD analysismean BJSD: 0.0205 -> 0.0245Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy