Agent Interfaces as an Evolvable Capability
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do or print all two thousand lines of a file through a shell to find one function. Both the interfaces and the knowledge of when to use each are built by hand which cannot keep pace with new applications workflows and models. We argue that interface design should itself be an agent capability.
Agent S4 and Experience-Driven Interface Construction
We introduce Agent S4 an autonomous computer-use scientist that builds Evolving Agent Interfaces from task experience. A meta-agent examines task agents trajectories on synthetic training tasks without success labels and constructs and revises interfaces and usage knowledge in a repository. Population-based evolution then selects which repositories to develop further by their performance on validation tasks the meta-agent never sees favoring changes that generalize beyond the seen tasks.
Results on OSWorld V2 and ScienceBoard
On OSWorld V2 Agent S4 with Qwen3.8-27B and the evolved repository of interfaces sets a new state of the art in open-source computer-use agents reaching 21.3 binary score 3.8 times the same model with fixed interfaces. This is above both GPT-5.5 (13.0) and Claude Opus 4.8 (20.6) at about 4.3 and 1.5 of their respective costs. On ScienceBoard the evolved interfaces improve the success rate from 41.4 to 58.6 with the same model.
Implications
These results suggest that useful interfaces can be evolved from experience making autonomous interface design a source of improvement complementary to advances in models and harnesses. We open-source our code at this https URL.