09:00 — Welcome
Levin Brinkmann & Dirk Wulff (Max Planck Institute for Human Development)
09:20 — Invited talk
Danica Dillion (University of North Carolina at Chapel Hill)
09:50 — Lightning talks (block A)
1. Indira Sen (University of Mannheim) — Evaluating Generative Social Simulations
2. Jelena Meyer (Max Planck Institute for Human Development) — When Reliability Misleads: Psychometric Scale Directionality Inflates Apparent Consistency in LLM Scale Responses
3. Jan Pfänder (Eawag — Swiss Federal Institute of Aquatic Science and Technology) — Predicting the Effects of a Megastudy with Behavioral Clones
4. Daniel Relihan (University of Southern California) — Where Do LLM Outputs Fall Relative to Human Severity Assessments? A Distributional Calibration Framework
5. Sharif Kazemi (World Bank Group) — Machine-Augmented Social Simulation (MASS): A Pipeline for Validating LLM In-Silico Predictions Against Statistical Baselines in Low-Resource Contexts
10:30 — Contributed talks (block 1)
1. Felipe Valencia-Clavijo (Dataplicada) — When Behavioral Similarity Misleads: Anchoring as a Behavioral Clone of Human Judgment in LLMs
2. Valentin Kriegmair (Max Planck Institute for Human Development) — Machine Individuality: Multi-Level Variance Partitioning Reveals Stable Behavioral Idiosyncrasies in Large Language Models
3. Faezeh Fadaei (University College Dublin) — Gender Dynamics and Homophily in a Social Network of LLM Agents
4. Louis Schiekiera (Humboldt-Universität zu Berlin) — Aligning Behavioral and Hidden-State Semantic Geometry in LLMs
12:05 — Invited talk
Marcel Binz (Helmholtz Munich)
13:45 — Lightning talks (block B)
1. Jessica Thompson (University of Oxford) — Using Behavioural Cloning to Accelerate Human Language Learning
2. Leonel Aguilar (ETH Zurich) — Beyond the Vessel: Ground-Truth Behavioural Traces for Foundational Models of Human Behaviour
3. Saeedeh Mohammadi (University College Dublin) — Bickering Machine: AI Feedback Enhances Community-Based Content Moderation Through Engagement with Counterarguments
4. Taisiia Tikhomirova (Max Planck Institute for Human Development) — Where Meaning Lives: Layer-Wise Accessibility of Psycholinguistic Features in Encoder and Decoder Language Models
14:10 — Invited talk
Nori Jacoby (Cornell University)
15:00 — Contributed talks (block 2)
1. Kristin Witte (Helmholtz Munich) — Evaluating Emotionally Loaded User-LLM Interactions Across Long Horizons
2. Maxime Saxena (University College London) — I Think, Therefore I Speculate: Reasoning-Induced Bubbles in LLM Financial Markets
3. Yannik Keller (Max Planck Institute for Human Development) — Improving Long-Run Group Welfare Through AI-Managed Sanctioning Institutions
4. Yaomin Jiang (Max Planck Institute for Human Development) — Emergent Strategic Communication in Goal-Optimized Language Agents
16:25 — Poster session
1. Aaron Petrasch (LMU Munich) — Validating Behavioral Clones: Testing Human–Machine Judgment Alignment With Psychometrics
2. Ajaykumar Manivannan (University of Leeds) — Generative Agent-based Modelling (GABM) Framework for Social Simulation: Understanding the Dynamics of Social Tipping When Persuaded by Two Competing Minorities
3. Ali Shiravand (École Normale Supérieure) — NORMARL: A Multi-agent Reinforcement Learning Framework for Adaptive Social Norms in Resource Sustainability
4. Beste Tasci (Helmholtz Munich) — Discovering Features of Human Decision-Making with Mechanistic Interpretability
5. Can Demircan (Helmholtz Munich) — Meta-learning as a Principle for Human-like Visual Representations
6. Florian Artinger (Deutsche Hochschule) — Efficient Predictions with Psychological AI: The Case of Recency and Satisficing
7. Frederico Pedrosa (Federal University of Minas Gerais) — The Hierarchical Structure of Musical Affect in Humans and AI Systems
8. Geoffroy Morlat (Sorbonne Université) — Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models
9. Jamie Cummins (University of Bern) — Analytic Flexibility Can Undermine the Simulation of Human Responses
10. Jana Gonnermann-Müller (Zuse Institute Berlin) — Persona Stability in LLM-Based Simulation
11. Joseph Kambeitz (University of Cologne) — Simulating Mental Health Trajectories with LLM-Based Generative Agents under Adverse Life Events
12. Lorenz Eckhard (University of Vienna) — Harnessing AI to Strengthen Vaccination Communication
13. Luca M. Schulze Buschoff (Helmholtz Munich) — Can Vision Language Models Learn Intuitive Physics from Interaction?
14. Ludwig Küster (HelloBetter) — Emotional Contagion in Human–Bot Interaction: Who Leads, Who Follows?
15. Luis Mienhardt (Max Planck Institute for Human Development) — Is Losing the Tail Detrimental?
16. Marco Pardini (University of Pisa) — Beyond Static Clones: An Affective Cognitive Architecture for Dynamic Machine Behavior
17. Maria Alejandra Ramirez (Max Planck Institute for Evolutionary Anthropology) — Non-Coercive Extortion via Artificial Agents
18. Max Pellert (Barcelona Supercomputing Center) — Large Language Models Replicate and Predict Human Cooperation Across Experiments in Game Theory
19. Maximilian Kreutner (University of Mannheim) — PopulationBench: On the Need for Measuring Large Language Models' Ability to Model Human Behavior
20. Nico Mutzner (University of Zurich) — Shadowing Humanity: The Limits of Synthetic Replication in Behavioral Experiments
21. Nicola Milano (University of Naples Federico II) — Large Language Models as Simulative Agents for Neurodivergent Adult Psychometric Profiles
22. Noah Schuster (University of Bath) — From Human Entrepreneurs to Behavioral Clones: Simulating Entrepreneurial Decision-Making
23. Raluca Rilla (Max Planck Institute for Human Development) — Modeling LLM Pollution in Online Behavioral Studies
24. Roya Esfandiari (BI Norwegian Business School) — Do Large Language Models Share Human Collective Blind Spots? Implications for Using LLMs as Human Participants
25. Ruggero Marino Lazzaroni (University of Graz) — Cog-Psych-Bench: A Benchmark for Large Language Models Performing Cognitive Psychology Decision Tasks
26. Ryutaro Mori (University of Tokyo) — Comparing Cooperative Behavior of Large Language Models and Humans in Voluntary Participation Public Goods Games
(Presenting on behalf of co-author Ilya Horiguchi.)
27. Tobias Rieger (TU Berlin) — Do LLM Agents Exhibit Algorithm Appreciation or Algorithm Aversion?
28. Tsz Kwan Wong (University of Warwick) — Human vs. Large Language Model-Based Sampling: Evidence from Large-Scale Replications
29. Yannik Keller (Max Planck Institute for Human Development) — Strategic Communication in Social Deduction Games Through Behavioral Cloning and Reinforcement Learning
17:45 — Panel — Open Questions and the Future
A short panel with our three invited speakers — Danica Dillion, Marcel Binz, and Nori Jacoby — on open methodological and scientific questions, and a brief look ahead to future events that continue the conversation.
18:15 — BBQ
A relaxed close to the day on the institute terrace, with food and drinks.