Hugging Face daily papers·9d agoFrom Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention#fine-tuning#foundation-models#long-horizon-tasks
MarkTechPost·14d agoContext Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks#agent-harness#claude-code#compaction 8 min2
Hugging Face daily papers·17d agoT1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks#agentic-ai#long-horizon-tasks#mixture-of-experts1
Hugging Face daily papers·19d agoEnvironments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks#environment-design#llm-agents#long-horizon-tasks1
