Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making
cs.CL
Submitted: 2026-06-24
Updated: 2026-11-01
Comments: Accepted to EMNLP 2026 (Main Conference)
Journal ref: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), pp. 13781-13800, 2026
DOI: 10.18653/2026.emnlp-main.599
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GPT-4 Technical Report
- Semantic World Models
- Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective
- ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
- World Modelling Improves Language Model Agents
- Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback
- Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling
- From Word to World: Can Large Language Models be Implicit Text-based World Models?
- DeepSeek-V3 Technical Report
- WebGPT: Browser-assisted question-answering with human feedback
- Qwen2.5 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Gemini: A Family of Highly Capable Multimodal Models
- Kimi K2: Open Agentic Intelligence
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Qwen3 Technical Report
- ReAct: Synergizing Reasoning and Acting in Language Models
- Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
- Agent Learning via Early Experience
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data