# CALM: A Calibrated LLM Choice Network Framework for Activity-Based Traveler Simulation

arXiv: https://arxiv.org/abs/2609.22252 · HTML: https://mlsanity.com/paper/2609.22252/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 6 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation](https://mlsanity.com/paper/2502.18712/) (2025)
- [Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework](https://mlsanity.com/paper/2412.06681/) (2024)
- [LLM-ABM for Transportation: Assessing the Potential of LLM Agents in System Analysis](https://mlsanity.com/paper/2503.22718/) (2025)
- [A Bayesian Optimization approach for calibrating large-scale activity-based transport models](https://mlsanity.com/paper/2302.03480/) (2023)
- [Bayesian Calibration for Activity Based Models](https://mlsanity.com/paper/2203.04414/) (2022)
- [LLMs for Human Mobility: Opportunities, Challenges, and Future Directions](https://mlsanity.com/paper/2603.12420/) (2026)
- [When Plausible Is Not Realistic: Evaluating Human Mobility in LLM-Based Urban Simulation](https://mlsanity.com/paper/2606.13835/) (2026)
- [CityBehavEx: A Scalable and Empirically Validated LLM-Assisted Urban Simulation Platform](https://mlsanity.com/paper/2607.12086/) (2026)

## Abstract (arXiv)

We present CALM, a reproducible hybrid framework that integrates an optional large language model (LLM) activity planner with calibrated stochastic choice, shared network feedback, memory and habit, typed feasibility checks, and deterministic offline replay. Unlike trip-mode classifiers or diary-only generators, CALM executes a closed traveler-day loop and evaluates each generative module against an empirical, reproducible baseline. On the 2024 New York City Citywide Mobility Survey (CMS), 110,691 seven-mode trips are split by respondent into 78,487 training and 32,204 holdout trips. Training-only alternative-specific constant calibration reduces mean holdout mode Jensen-Shannon divergence from 0.15599 to 0.00394 across ten seeds. A matched live-LLM ablation then quantifies trade-offs among aggregate fit, temporal fit, behavioral persistence, and feasibility, while frozen prompt-response pairs support deterministic replay of downstream simulation. Controlled weather, delay, fare, and parking ladders further demonstrate consistent and interpretable responses under intervention. CALM contributes a reproducible protocol for integrating and evaluating generative planners in traveler simulation through person-disjoint calibration, matched module ablation, controlled stress testing, and end-to-end traceability.