Papers

Filtered to task-preserving transformations · 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

Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report

47 upvotes · 22 AUG 2026 · TaoLive AIGC LLM Team, Yuhan Sun, Wenhao Lin et al.

This paper trains compact AI models to adapt quickly to changing digital avatar "harnesses" that define the tasks and tools available to the model, improving performance and reducing latency. Practitioners caring about real-time AI applications, such as chatbots or virtual assistants, might find this approach useful.

digital avatar agentscontinual learningreinforcement learninglow-latency modelstask-preserving transformations