EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models
cs.CL
Submitted: 2026-10-02
Updated: 2026-10-02
Terminology
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- AI Agents as Policymakers in Simulated Epidemics
- On the limits of agency in agent-based models
- Agentic Framework for Epidemiological Modeling
- EpiNarrate: Agentic Generation of Grounded Narratives from Epidemiological Scenario Projections
- Mastering Diverse Domains through World Models
- Temporal Difference Learning for Model Predictive Control
- Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancy
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- Planning Multiple Epidemic Interventions with Reinforcement Learning
- EpiPlanAgent: Agentic Automated Epidemic Response Planning
- Toward World Models for Epidemiology
- Transformers are Sample-Efficient World Models
- MolWorld: Molecule World Models for Actionable Molecular Optimization
- Coordinated Pandemic Control with Large Language Model Agents as Policymaking Assistants
- Reinforced Epidemic Control: Saving Both Lives and Economy
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Epidemic Modeling with Generative Agents
- Optimizing Interventions for Agent-Based Infectious Disease Simulations
- AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
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