agentic scaffolding
External supports like training curricula, tool selection, and success verifiers enable agents to handle long-horizon or out-of-distribution tasks.
- Papers
- 4
- Released code
- 0
- First seen
- Sept 2026
- Latest
- Sept 2026
4 papers in the last two months, against 0 in the two before.
The papers
Most central to this idea first, not most recent.
- Industrycs.AI
Coding-agent harness choices should match model skill and context budget
UMass Amherst, Zoom Video Communications · Sept 2026
- Independentcs.AI
Training agents to combine graphical interfaces and commands improves efficiency
Sept 2026
- Chinese Techcs.CL
Hybrid agents learn to recreate software across five computing platforms
Alibaba Token Hub, Alibaba Group · Sept 2026
- Top Universitycs.RO
Targeted subtask reinforcement learning improves long-horizon robot manipulation
UT Austin, Autel US · Sept 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.