• Computer Science > Artificial Intelligence [Submitted on 3 Feb 2026] Title:General learned delegation by clones View PDF HTML (experimental)Abstract:Frontier language models improve with additional test-time computation, but serial reasoning or uncoordinated parallel sampling can be compute-inefficient under fixed inference budgets. • We propose SELFCEST, which equips a base model with the ability to spawn same-weight clones in separate parallel contexts by agentic reinforcement learning. • Training is end-to-end under a global task reward with shared-parameter rollouts, yielding a learned controller that allocates both generation and context budget across branches. • Across challenging math reasoning benchmarks and long-context multi-hop QA, SELFCEST improves the accuracy-cost Pareto frontier relative to monolithic baselines at matched inference budget, and exhibits out-of-distribution generalization in both domains. • References & Citations export BibTeX citation Loading… • Bibliographic and Citation Tools Bibliographic Explorer (What is the Explorer?) Connected Papers (What is Connected Papers?) Litmaps (What is Litmaps?) scite Smart Citations (What are Smart Citations?) Code, Data and Media Associated with this Article alphaXiv (What is alphaXiv?) CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub (What is DagsHub?) Gotit.pub (What is GotitPub?) Hugging Face (What is Huggingface?) Papers with Code (What is Papers with Code?) ScienceCast (What is ScienceCast?) Demos Rec

Article Summaries:

  • Computer Science > Artificial Intelligence [Submitted on 3 Feb 2026] Title:General learned delegation by clones View PDF HTML (experimental)Abstract:Frontier language models improve with additional test-time computation, but serial reasoning or uncoordinated parallel sampling can be compute-inefficient under fixed inference budgets. We propose SELFCEST, which equips a base model with the ability to spawn same-weight clones in separate parallel contexts by agentic reinforcement learning. Training is end-to-end under a global task reward with shared-parameter rollouts, yielding a learned control

Sources: