OdysSim: Building Foundation Models for Human Behavior Simulation

arXiv:2606.14199 · cs.CL, cs.AI, cs.LG · Submitted 2026-06-12 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-06-12

Updated: 2026-09-07

Comments: 34 pages. Code: https://github.com/sunnweiwei/OdysSim ; Models and data: https://huggingface.co/collections/cmu-lti/odyssim ; v2: Corrected two bibliography entries

Code: https://github.com/sunnweiwei/OdysSim

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 46× in this paper · explained in 2 episodes
• GRPO — 36× in this paper · explained in 6 episodes
• Distillation — 29× in this paper · explained in 2 episodes
• Alignment — 21× in this paper · explained in 1 episode
• Foundation Model — 17× in this paper · explained in 3 episodes
• Foundation Models — 13× in this paper · explained in 7 episodes
• LLM judge — 13× in this paper · explained in 2 episodes
• Ablation — 12× in this paper · explained in 1 episode
• Accuracy — 12× in this paper · explained in 1 episode
• Fidelity — 10× in this paper · explained in 2 episodes
• Grounding — 8× in this paper · explained in 3 episodes
• Trace — 7× in this paper · explained in 2 episodes
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Provenance — 4× in this paper · explained in 4 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Calibration — 3× in this paper · explained in 7 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Reward Hacking — 3× in this paper · explained in 8 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Agentic Task — 2× in this paper · explained in 1 episode
• Agentic Tasks — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• GRPO Objective — 2× in this paper · explained in 2 episodes
• Meeting of the Association for Computational Linguistics — 2× in this paper
• Verifiable Rewards — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Alignment Scores — 1× in this paper · explained in 1 episode
• Digital Twin — 1× in this paper · explained in 5 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Lexical Diversity — 1× in this paper · explained in 2 episodes
• Model Merging — 1× in this paper · explained in 2 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes
• User Simulation Index — 1× in this paper
• alpha — 1× in this paper · explained in 1 episode

Sources

• Out of One, Many: Using Language Models to Simulate Human Samples
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Centaur: a foundation model of human cognition
• ConvoKit: A Toolkit for the Analysis of Conversations
• CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems
• Persona Vectors: Monitoring and Controlling Character Traits in Language Models
• Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
• SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?
• TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation
• Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences
• Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
• HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models
• Reinforcement Learning via Self-Distillation
• One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence
• Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
• FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions
• The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
• PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions
• OpenAssistant Conversations -- Democratizing Large Language Model Alignment
• HumanLLM: Towards Personalized Understanding and Simulation of Human Nature

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering