Papers

Filtered to reinforcement-learning · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

Sample-Efficient Learning from Agent Experience

17 upvotes · 23 JUL 2026 · Chenhui Gou, Haoqin Tu, Yunhao Fang et al.

This paper develops a method called Experience Distillation that allows agents to learn from their own interaction histories without needing additional environment interactions, making learning more sample-efficient. Practitioners might care about this because it can improve the performance of agents in complex environments with limited resources.

continual learningin-context learningreinforcement-learningagent experiencesample efficiency

Interactive Training 2: Auditable Control Plane for Live Model Training

17 upvotes · 17 JUL 2026 · Wentao Zhang, Xuanhe Pan, Han Zhou et al.

This paper introduces a new system for controlling live machine learning model training, allowing humans and automated controllers to interact with the training process through a shared interface, and providing a clear audit trail of changes and outcomes. Practitioners might care because it enables more transparent and accountable training processes.

auditable control planelive model trainingNLP workflowsreinforcement-learningtraining interfaces