Papers

Filtered to task validation · 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

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

115 upvotes · 19 AUG 2026 · Kou Shi, Zun Wang, Qisheng Su et al.

This paper develops a method to generate high-quality terminal tasks for training agents, ensuring that the tasks accurately reflect the original instruction and environment, and providing a way to validate and improve the generated tasks. Practitioners in AI and robotics may care about this work because it addresses a common challenge in training terminal agents.

continual learningscalable executable supervisionterminal task synthesismulti-stage synthesisagent trainingtask validation