# Improving Behavioral Alignment in LLM Social Simulations via Context Formation and Navigation

arXiv: https://arxiv.org/abs/2601.01546 · HTML: https://mlsanity.com/paper/2601.01546/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 82 references that are in the map.
- First posted on arXiv 4 Jan 2026.

## Builds on (most cited first, 26 of 26)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [Generative artificial intelligence enhances creativity but reduces the diversity of novel content](https://mlsanity.com/paper/2312.00506/) (2023)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspective](https://mlsanity.com/paper/2312.15524/) (2023)
- [Do LLM Agents Exhibit Social Behavior?](https://mlsanity.com/paper/2312.15198/) (2023)
- [AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction](https://mlsanity.com/paper/2305.09620/) (2023)
- [TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets](https://mlsanity.com/paper/2502.01506/) (2025)
- [Automated Paper Screening for Clinical Reviews Using Large Language Models](https://mlsanity.com/paper/2305.00844/) (2023)
- [Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina](https://mlsanity.com/paper/2410.19599/) (2024)
- [Large Language Models for Market Research: A Data-augmentation Approach](https://mlsanity.com/paper/2412.19363/) (2024)
- [AgentA/B: Automated and Scalable Web A/BTesting with Interactive LLM Agents](https://mlsanity.com/paper/2504.09723/) (2025)
- [LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments](https://mlsanity.com/paper/2406.02611/) (2024)
- [The Value of AI-Generated Metadata for UGC Platforms: Evidence from a Large-scale Field Experiment](https://mlsanity.com/paper/2412.18337/) (2024)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used to simulate human behavior in experimental settings, but they systematically diverge from human decisions in complex decision-making environments, where participants must anticipate others' actions and form beliefs based on observed behavior. We propose a two-stage framework for improving behavioral alignment. The first stage, context formation, explicitly specifies the experimental design to establish an accurate representation of the decision task and its context. The second stage, context navigation, guides the reasoning process within that representation to make decisions. We validate this framework through a focal replication of a sequential purchasing game with quality signaling (Kremer and Debo, 2016), extending to a crowdfunding game with costly signaling (Cason et al., 2025) and a demand-estimation task (Gui and Toubia, 2025) to test generalizability across decision environments. Across four state-of-the-art (SOTA) models (GPT-4o, GPT-5, Claude-4.0-Sonnet-Thinking, DeepSeek-R1), we find that complex decision-making environments require both stages to achieve behavioral alignment with human benchmarks, whereas the simpler demand-estimation task requires only context formation. Our findings clarify when each stage is necessary and provide a systematic approach for designing and diagnosing LLM social simulations as complements to human subjects in behavioral research.