AAWM builds training targets for world models by retrieving and synthesizing transition evidence based on the policy's self-identified decision needs at each state.
Current agents fail to leverage world model as tool for foresight.arXivpreprint
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
Qwen-AgentWorld are language world models that simulate multi-domain agent environments and boost general agent capabilities via decoupled RL simulation and unified foundation model training.
Presents PF-OPSD self-distillation method and two new benchmarks showing 10%+ gains by training models to invoke and integrate visual future simulations alongside abstract MLLM reasoning without true futures at test time.
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
World models enable efficient AI planning but create risks from adversarial corruption, goal misgeneralization, and human bias, demonstrated via attacks that amplify errors and reduce rewards on models like RSSM and DreamerV3.
WorldEvolver uses episodic memory, semantic memory, and selective foresight to self-evolve world models at test time, achieving top prediction accuracy and agent success on ALFWorld and ScienceWorld benchmarks.
Einstein World Models integrate visual rollouts from a callable world-module into LLM reasoning traces to support complex thought beyond language.
citing papers explorer
-
Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making
AAWM builds training targets for world models by retrieving and synthesizing transition evidence based on the policy's self-identified decision needs at each state.
-
Qwen-AgentWorld: Language World Models for General Agents
Qwen-AgentWorld are language world models that simulate multi-domain agent environments and boost general agent capabilities via decoupled RL simulation and unified foundation model training.
-
World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning
Presents PF-OPSD self-distillation method and two new benchmarks showing 10%+ gains by training models to invoke and integrate visual future simulations alongside abstract MLLM reasoning without true futures at test time.
-
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
-
Safety, Security, and Cognitive Risks in World Models
World models enable efficient AI planning but create risks from adversarial corruption, goal misgeneralization, and human bias, demonstrated via attacks that amplify errors and reduce rewards on models like RSSM and DreamerV3.
-
Self-Evolving World Models for LLM Agent Planning
WorldEvolver uses episodic memory, semantic memory, and selective foresight to self-evolve world models at test time, achieving top prediction accuracy and agent success on ALFWorld and ScienceWorld benchmarks.
-
Einstein World Models
Einstein World Models integrate visual rollouts from a callable world-module into LLM reasoning traces to support complex thought beyond language.