Tag
This paper proposes Dreamer-SAC, a model-based reinforcement learning framework that integrates a recurrent state-space world model with soft actor-critic in latent space for sample-efficient autonomous driving. It outperforms DreamerV3, SAC, and PPO baselines while requiring fewer real environment interactions.
Proposes Experience Distillation, a method that internalizes in-context learning gains from agent interaction histories into model weights without requiring additional environment interaction, achieving significant sample efficiency improvements on software engineering and text-adventure tasks.
TRACE is a new self-improvement approach where an AI agent identifies the missing capabilities behind its own failures and trains itself to address them. TRACE-trained Qwen3.6-27B achieves 73.2% on SWE-bench Verified, outperforming much larger models with fewer training rollouts.
This paper presents a multi-objective Bayesian optimization approach to automate weight selection in reinforcement learning for energy-aware control, demonstrating superior sample efficiency over grid search on a physical Quanser Aero 2 testbed.
Proposes Agentic-Ideation, a framework for efficient synthesis of agentic trajectories to train LLMs for scientific ideation, achieving over 10x improvement in sample efficiency and outperforming existing workflow-based baselines.
AC-ODM uses reinforcement learning to dynamically optimize pretraining data composition for LLMs, achieving faster convergence and higher downstream accuracy with negligible computational overhead.
This paper identifies a failure mode called PhysHack in LLM-based LEGO assembly generation and proposes PVPO, a sample-efficient reinforcement learning method with model-based data selection that improves physical and semantic alignment using only a small fraction of training data.
ChainzRule introduces a neural architecture with learnable polynomial layers and differential regularization, achieving sample-efficient, robust performance across tabular, NLP, and vision tasks with results on Pima Diabetes, SST-5, Yelp Full, and CIFAR-10-C.