Subjective-Graph LLM Agents for Simulating Uncertainty in Classroom Social Perception

[Submitted on 21 Mar 2026 (v1), last revised 23 Jun 2026 (this version, v2)]

View PDF HTML (experimental)

Abstract:Social actors do not observe a common social world: each individual forms judgments from a partial and potentially distorted view of the surrounding network. We study whether graph-local evidence and credibility-weighted communication can generate persistent distortions in perceived academic standing, even when agents repeatedly receive objective performance signals. We introduce a data-constrained multi-agent framework in which LLM agents operate through individualized subjective graphs that determine peer visibility, evidence access, and interaction opportunities. Agents exchange uncertainty-annotated assessments, evaluate message credibility, and maintain explicit Gaussian belief states updated through Bayesian fusion. We evaluate the framework on 12 middle-school classrooms comprising 482 students, using questionnaire-derived social information and six consecutive examinations. On the Social-Observed subset (n=419), collective ranking error increases from 0.066 \pm 0.008 to 0.124 \pm 0.009 across six epochs despite repeated exam-based anchoring. Ablations associate individualized visibility and LLM-based trust gating with more stable long-horizon behavior, while constrained retrieval primarily safeguards against global-information leakage. Compared with evaluated DeGroot configurations, the proposed framework achieves lower final ranking error; those DeGroot configurations exhibit near-zero terminal opinion diversity. These findings establish subjective-graph LLM agents as a mechanism-oriented framework for data-constrained simulated social perception. Code is available at this https URL.

Submission history

From: Xinshan Jiao [view email]
[v1] Sat, 21 Mar 2026 10:47:09 UTC (2,294 KB)
[v2] Tue, 23 Jun 2026 07:54:44 UTC (1,607 KB)