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

arXiv: https://arxiv.org/abs/2603.20750 · HTML: https://mlsanity.com/paper/2603.20750/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 18 of 18)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models](https://mlsanity.com/paper/2411.19443/) (2024)
- [Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models](https://mlsanity.com/paper/2503.17523/) (2025)
- [Multi-agent Reinforcement Learning: A Comprehensive Survey](https://mlsanity.com/paper/2312.10256/) (2023)
- [Conditional Neural Relational Inference for Interacting Systems](https://mlsanity.com/paper/2106.11083/) (2021)
- [Agent-Based Modelling Meets Generative AI in Social Network Simulations](https://mlsanity.com/paper/2411.16031/) (2024)
- [Population-Aligned Persona Generation for LLM-based Social Simulation](https://mlsanity.com/paper/2509.10127/) (2025)
- [Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research](https://mlsanity.com/paper/2506.01839/) (2025)
- [Are LLM Belief Updates Consistent with Bayes' Theorem?](https://mlsanity.com/paper/2507.17951/) (2025)
- [BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modeling](https://mlsanity.com/paper/2406.05516/) (2024)
- [Large Language Models for Agent-Based Modelling: Current and possible uses across the modelling cycle](https://mlsanity.com/paper/2507.05723/) (2025)
- [LLM Agent-Based Simulation of Student Activities and Mental Health Using Smartphone Sensing Data](https://mlsanity.com/paper/2508.02679/) (2025)

## Abstract (arXiv)

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 ± 0.008 to 0.124 ± 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.