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

Source: [Subjective-Graph LLM Agents for Simulating Uncertainty in Classroom Social Perception](<https://www.sota2.com/research/paper/69c21a690636e5bf4afc4692>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-25T05:00:21.026Z

Authors: Jinming Yang, Xinyu Jiang, Xinshan Jiao, Xinping Zhang

Published: 2026-03-21T10:47:09.000Z

## 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 https://anonymous.4open.science/r/Rashomonomon-0126.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Social Perception Ranking on Middle-school classroom social networks Epoch 6 (test)](<https://www.sota2.com/research/sota/social-perception-ranking-on-middle-school-classroom-social-networks-epoch-6-test.md>): Social Perception Ranking; Middle-school classroom social networks Epoch 6 (test); DPAE6: 0.124.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.20750>)

[PDF](<https://arxiv.org/pdf/2603.20750.pdf>)
