Papers

Filtered to SFT (stable flow of tasks) · 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

NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs

14 upvotes · 22 JUL 2026 · Jiarong Zhao, Zhikai Lei, Zhiheng Xi et al.

This paper develops a framework called NexForge that helps train more capable artificial agents by automatically generating a large number of tasks and training data, without requiring a lot of manual setup. Practitioners might care because it can improve the performance of their own agent models.

continual learningLLMsagent trainingtask synthesisrequirement-driven methodsSFT (stable flow of tasks)