Introduces textual belief states and factorized GRPO to enforce strict latent state mediation in text-based world models, yielding preserved prediction accuracy with large gains in representation quality and rollout performance on TextWorld and ScienceWorld.
arXiv preprint arXiv:2512.18832 , year=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 11roles
background 2polarities
background 2representative citing papers
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.
PaW co-trains policy and world modeling on standard RL rollouts using action-entropy data selection, noise-tolerant loss, and reward-adaptive balancing, yielding consistent gains on three agent benchmarks.
COMAP co-evolves textual world models and agent policies for LLMs through on-policy self-distillation, yielding up to 16.75% relative gains on embodied planning, web navigation, and tool-use tasks.
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
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.
A three-stage training pipeline internalizes world-model simulation and success estimation in LLM agents for improved planning on search and math tasks.
A staged LLM pipeline synthesizes verifiable discrete-event world models from natural language specifications using the DEVS formalism for long-horizon consistency in LLM agents.
World models trained on delta text, full text, diffusion images, and renderable code achieve SoTA on two benchmarks and improve downstream GUI agent performance on three mobile datasets with modality-specific strengths.
Reasoning in language models should be measured by the faithfulness and validity of their multi-step search processes and intermediate traces, not final-answer accuracy.
A survey proposing a three-level capability taxonomy (L1 Predictor, L2 Simulator, L3 Evolver) for world models across physical, digital, social, and scientific domains.
citing papers explorer
-
Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation
Introduces textual belief states and factorized GRPO to enforce strict latent state mediation in text-based world models, yielding preserved prediction accuracy with large gains in representation quality and rollout performance on TextWorld and ScienceWorld.
-
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.
-
Policy and World Modeling Co-Training for Language Agents
PaW co-trains policy and world modeling on standard RL rollouts using action-entropy data selection, noise-tolerant loss, and reward-adaptive balancing, yielding consistent gains on three agent benchmarks.
-
COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
COMAP co-evolves textual world models and agent policies for LLMs through on-policy self-distillation, yielding up to 16.75% relative gains on embodied planning, web navigation, and tool-use tasks.
-
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
-
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.
-
Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning
A three-stage training pipeline internalizes world-model simulation and success estimation in LLM agents for improved planning on search and math tasks.
-
Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism
A staged LLM pipeline synthesizes verifiable discrete-event world models from natural language specifications using the DEVS formalism for long-horizon consistency in LLM agents.
-
How Mobile World Model Guides GUI Agents?
World models trained on delta text, full text, diffusion images, and renderable code achieve SoTA on two benchmarks and improve downstream GUI agent performance on three mobile datasets with modality-specific strengths.
-
Measuring AI Reasoning: A Guide for Researchers
Reasoning in language models should be measured by the faithfulness and validity of their multi-step search processes and intermediate traces, not final-answer accuracy.
-
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
A survey proposing a three-level capability taxonomy (L1 Predictor, L2 Simulator, L3 Evolver) for world models across physical, digital, social, and scientific domains.