Papers

Filtered to open-ended self-improvement · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

SPADE: Self-Play in Adaptive Synthetic Executable Environments

47 upvotes · 19 AUG 2026 · Bo Liu, Simon Yu, Yiding Jiang et al.

This paper introduces SPADE, a self-play framework that enables language agents to learn from adaptive, self-generated environments, allowing them to improve continuously without fixed goal distributions. Practitioners might care because SPADE can lead to more robust and open-ended AI models.

self-playadaptive environmentslanguage modelsreinforcement learningopen-ended self-improvement