Papers

Filtered to learning paradigm · 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

Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement

59 upvotes · 11 SEP 2026 · Hongyao Tang, Yi Ma, Pengyi Li et al.

This paper proposes a single framework that can describe both iterative policy improvement and recursive self-improvement, which are key concepts in AI and machine learning, and helps analyze and design new systems that can learn and improve over time.

agent iterationpolicy improvementrecursive self-improvementformal frameworklearning paradigm