Newest papers

Evolving Agent Interfaces

Saaket Agashe, Yuzhe Yang, Gonzalo Gonzalez-Pumariega, Bhuvan Chandra Koduru, Chih-Lun Li, Jiachen Yang, Ang Li, Xin Eric Wang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28601 · cited by 0 works (OpenAlex) · open-access PDF

Korean

컴퓨터 사용자 정의 에이전트는 인간이 제공하는 인터페이스에 의해 제한됩니다. 에이전트는 한 줄의 코드가 할 때 세포에 대 한 세포 정의 할 수 있습니다, 또는 하나의 함수를 통해 파일의 모든 천 줄을 인쇄합니다. 개방 된 작업 경험에서 진화 에이전트 인터페이스를 구축하는 독립적 인 컴퓨터 사용 과학자 S4를 소개합니다. 메타 에이전트는 합성 훈련 작업에 대한 작업 에이전트의 경로를 수행 할 수없는 손으로 구축되며, 새로운 애플리케이션, 작업 흐름 및 모델과 속도를 유지할 수 있습니다. 우리는 인터페이스 디자인 자체가 에이전트 기능이어야한다고 주장합니다. 인구 기반 진화는 메타 에이전트 인터페이스가 결코 볼 수없는

Machine translation (Meta M2M100); the English original follows.

Abstract

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. 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. 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. 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 https://github.com/simular-ai/agent-s.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Task (project management), Interface (matter), Code (set theory), Human–computer interaction, Autonomous agent

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange