PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization

• URL: http://arxiv.org/abs/2603.19649v1
• Date: Fri, 20 Mar 2026 05:20:39 GMT
• Title: PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization
• Abstract summary: PolicySim is an LLM-based social simulation sandbox for the proactive assessment and optimization of intervention policies.<n>We show that PolicySim can accurately simulate platform ecosystems at both micro and macro levels.
• Score: 22.490419080772586
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Social platforms serve as central hubs for information exchange, where user behaviors and platform interventions jointly shape opinions. However, intervention policies like recommendation and content filtering, can unintentionally amplify echo chambers and polarization, posing significant societal risks. Proactively evaluating the impact of such policies is therefore crucial. Existing approaches primarily rely on reactive online A/B testing, where risks are identified only after deployment, making risk identification delayed and costly. LLM-based social simulations offer a promising pre-deployment alternative, but current methods fall short in realistically modeling platform interventions and incorporating feedback from the platform. Bridging these gaps is essential for building actionable frameworks to assess and optimize platform policies. To this end, we propose PolicySim, an LLM-based social simulation sandbox for the proactive assessment and optimization of intervention policies. PolicySim models the bidirectional dynamics between user behavior and platform interventions through two key components: (1) a user agent module refined via supervised fine-tuning (SFT) and direct preference optimization (DPO) to achieve platform-specific behavioral realism; and (2) an adaptive intervention module that employs a contextual bandit with message passing to capture dynamic network structures. Experiments show that PolicySim can accurately simulate platform ecosystems at both micro and macro levels and support effective intervention policy.

Related papers

• ALSO: Adversarial Online Strategy Optimization for Social Agents [63.84788516416339]
  We propose textbfALSO (textbfAdrial ontextbfLine textbfStrategy textbfOptimization) as the first framework for online strategy optimization in social simulation.<n> ALSO formulates multi-turn interaction as an adversarial bandit problem, where combinations of static personas and dynamic strategy instructions are treated as arms.<n>Also introduces a lightweight neural surrogate to predict rewards from interaction histories, enabling sample-efficient exploration and continuous online adaptation.
  arXiv  Detail & Related papers  (2026-05-15T09:25:15Z)
• LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms [12.693132563364342]
  Short-video platforms are closed-loop, human-in-the-loop ecosystems where policy, creator incentives, and user behavior co-evolve.<n>We propose a large language model (LLM)-augmented digital twin for short-video platforms with a modular four-twin architecture.
  arXiv  Detail & Related papers  (2026-03-11T21:50:21Z)
• Position: AI Agents Are Not (Yet) a Panacea for Social Simulation [62.891898598784415]
  Recent advances in large language models (LLMs) have spurred growing interest in using LLM-integrated agents for social simulation.<n>This position paper argues that LLM-based agents are not (yet) a panacea for social simulation.
  arXiv  Detail & Related papers  (2026-02-19T06:35:07Z)
• Beyond Offline A/B Testing: Context-Aware Agent Simulation for Recommender System Evaluation [0.7031557790463293]
  We introduce ContextSim, an agent framework that simulates believable user proxies by anchoring interactions in daily life activities.<n>To align preferences with genuine humans, we model agents' internal thoughts and enforce consistency at both the action and trajectory levels.
  arXiv  Detail & Related papers  (2026-01-26T05:01:00Z)
• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• Integrating LLM and Diffusion-Based Agents for Social Simulation [28.21329943306884]
  We propose a hybrid simulation framework that strategically integrates large language model (LLM)-driven agents with diffusion model-based agents.<n>Our framework outperforms existing methods in prediction accuracy, validating the effectiveness of its modular design.
  arXiv  Detail & Related papers  (2025-10-18T06:23:22Z)
• Logarithmic Smoothing for Adaptive PAC-Bayesian Off-Policy Learning [4.48890356952206]
  Off-policy learning serves as the primary framework for learning optimal policies from logged interactions.<n>We extend this framework to the adaptive scenario using tools from online PAC-Bayesian theory.
  arXiv  Detail & Related papers  (2025-06-12T12:54:09Z)
• Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems [37.15496324034216]
  RecInter is a novel agent-based simulation platform for recommender systems.<n>In RecInter, simulated user actions (e.g., likes, reviews, purchases) dynamically update item attributes in real-time.<n> Merchant Agents can reply, fostering a more realistic and evolving ecosystem.
  arXiv  Detail & Related papers  (2025-05-22T09:14:23Z)
• Large Language Model driven Policy Exploration for Recommender Systems [50.70228564385797]
  offline RL policies trained on static user data are vulnerable to distribution shift when deployed in dynamic online environments.<n>Online RL-based RS also face challenges in production deployment due to the risks of exposing users to untrained or unstable policies.<n>Large Language Models (LLMs) offer a promising solution to mimic user objectives and preferences for pre-training policies offline.<n>We propose an Interaction-Augmented Learned Policy (iALP) that utilizes user preferences distilled from an LLM.
  arXiv  Detail & Related papers  (2025-01-23T16:37:44Z)
• SDPO: Segment-Level Direct Preference Optimization for Social Agents [56.970902914217156]
  Social agents powered by large language models (LLMs) can simulate human social behaviors but fall short in handling complex social dialogues.<n>We propose Segment-Level Direct Preference Optimization (SDPO), which dynamically select key segments within interactions to optimize multi-turn agent behavior.
  arXiv  Detail & Related papers  (2025-01-03T14:09:46Z)
• SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent [45.41401816514924]
  We propose an innovative framework, SRAP-Agent, which integrates Large Language Models (LLMs) into economic simulations. We conduct extensive policy simulation experiments to verify the feasibility and effectiveness of the SRAP-Agent.
  arXiv  Detail & Related papers  (2024-10-18T03:43:42Z)
• Building a Foundation for Data-Driven, Interpretable, and Robust Policy Design using the AI Economist [67.08543240320756]
  We show that the AI Economist framework enables effective, flexible, and interpretable policy design using two-level reinforcement learning and data-driven simulations. We find that log-linear policies trained using RL significantly improve social welfare, based on both public health and economic outcomes, compared to past outcomes.
  arXiv  Detail & Related papers  (2021-08-06T01:30:41Z)
• Non-Stationary Off-Policy Optimization [50.41335279896062]
  We study the novel problem of off-policy optimization in piecewise-stationary contextual bandits. In the offline learning phase, we partition logged data into categorical latent states and learn a near-optimal sub-policy for each state. In the online deployment phase, we adaptively switch between the learned sub-policies based on their performance.
  arXiv  Detail & Related papers  (2020-06-15T09:16:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.