Related papers: Code World Models for Parameter Control in Evoluti…

In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, {\Delta}t, and training over a diverse range of {\Delta}t values --…

Recent works have shown that gradient-update alignment is a powerful signal for modulating optimizer updates, often leading to faster training. We promote this update-wise heuristic as a mathematically grounded principle for selecting and…

With the decline of Moore's law, optimizing program performance has become a major focus of software research. However, high-level optimizations such as API and algorithm changes remain elusive due to the difficulty of understanding the…

Recent work has demonstrated the promise of orchestrating large language models (LLMs) within evolutionary and agentic optimization systems. However, the mechanisms driving these optimization gains remain poorly understood. In this work, we…

This paper introduces the concept of Language-Guided World Models (LWMs) -- probabilistic models that can simulate environments by reading texts. Agents equipped with these models provide humans with more extensive and efficient control,…

The scaling law, a cornerstone of Large Language Model (LLM) development, predicts improvements in model performance with increasing computational resources. Yet, while empirically validated, its theoretical underpinnings remain poorly…

Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a…

Large Language Models (LLMs) have recently shown strong reasoning and generalization capabilities, motivating their use as decision-making policies in complex environments. StarCraft II (SC2), with its massive state-action space and partial…

While Large Language Models (LLMs) hold promise to become autonomous agents, they often explore suboptimally in sequential decision-making. Recent work has sought to enhance this capability via supervised fine-tuning (SFT) or reinforcement…

This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conducted pre-release testing across domains identified in our Frontier AI Framework as…

Efficient exploration remains a central challenge in reinforcement learning (RL), particularly in sparse-reward environments. We introduce Optimistic World Models (OWMs), a principled and scalable framework for optimistic exploration that…

Can large language models (LLMs) directly serve as powerful world models for model-based agents? While the gaps between the prior knowledge of LLMs and the specified environment's dynamics do exist, our study reveals that the gaps can be…

LLMs demonstrate remarkable reasoning capabilities, yet whether they utilize internal world models or rely on sophisticated pattern matching remains open. We study LLMs through the lens of robustness of their code understanding using a…

In model-based learning, the agent learns behaviors by simulating trajectories based on world model predictions. Standard world models typically learn a stationary transition function that maps states and actions to next states, when an…

Reinforcement learning from large-scale offline datasets provides us with the ability to learn policies without potentially unsafe or impractical exploration. Significant progress has been made in the past few years in dealing with the…

Long-horizon clinical simulation -- predicting how a patient's physiology evolves over years under specified interventions -- is central to chronic-disease care, yet existing electronic health record (EHR) models are predominantly…

Backpropagation dominates modern machine learning, yet it is not the only principled method for optimizing dynamical systems. We propose Kalman World Models (KWM), a class of learned state-space models trained via recursive Bayesian…

Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it…

Large language models (LLMs) have recently gained much attention in building autonomous agents. However, the performance of current LLM-based web agents in long-horizon tasks is far from optimal, often yielding errors such as repeatedly…

The performance of learned robot visuomotor policies is heavily dependent on the size and quality of the training dataset. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action…