Recursive Agent Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909022888656896 |
|---|---|
| author | Gandhi, Apurva Chakraborty, Satyaki Wang, Xiangjun Kumar, Aviral Neubig, Graham |
| author_facet | Gandhi, Apurva Chakraborty, Satyaki Wang, Xiangjun Kumar, Aviral Neubig, Graham |
| contents | We introduce Recursive Agent Optimization (RAO), a reinforcement learning approach for training recursive agents: agents that can spawn and delegate sub-tasks to new instantiations of themselves recursively. Recursive agents implement an inference-time scaling algorithm that naturally allows agents to scale to longer contexts and generalize to more difficult problems via divide-and-conquer. RAO provides a method to train models to best take advantage of such recursive inference, teaching agents when and how to delegate and communicate. We find that recursive agents trained in this way enjoy better training efficiency, can scale to tasks that go beyond the model's context window, generalize to tasks much harder than the ones the agent was trained on, and can enjoy reduced wall-clock time compared to single-agent systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06639 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Recursive Agent Optimization Gandhi, Apurva Chakraborty, Satyaki Wang, Xiangjun Kumar, Aviral Neubig, Graham Machine Learning Artificial Intelligence Computation and Language Multiagent Systems We introduce Recursive Agent Optimization (RAO), a reinforcement learning approach for training recursive agents: agents that can spawn and delegate sub-tasks to new instantiations of themselves recursively. Recursive agents implement an inference-time scaling algorithm that naturally allows agents to scale to longer contexts and generalize to more difficult problems via divide-and-conquer. RAO provides a method to train models to best take advantage of such recursive inference, teaching agents when and how to delegate and communicate. We find that recursive agents trained in this way enjoy better training efficiency, can scale to tasks that go beyond the model's context window, generalize to tasks much harder than the ones the agent was trained on, and can enjoy reduced wall-clock time compared to single-agent systems. |
| title | Recursive Agent Optimization |
| topic | Machine Learning Artificial Intelligence Computation and Language Multiagent Systems |
| url | https://arxiv.org/abs/2605.06639 |