# A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution

arXiv: https://arxiv.org/abs/2610.15765 · HTML: https://mlsanity.com/paper/2610.15765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 32 references that are in the map.
- First posted on arXiv 11 Oct 2026.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 28 of 28)

- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale](https://mlsanity.com/paper/2409.08264/) (2024)
- [Agent S: An Open Agentic Framework that Uses Computers Like a Human](https://mlsanity.com/paper/2410.08164/) (2024)
- [Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks](https://mlsanity.com/paper/2501.11733/) (2025)
- [Beyond Browsing: API-Based Web Agents](https://mlsanity.com/paper/2410.16464/) (2024)
- [UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction](https://mlsanity.com/paper/2503.15661/) (2025)
- [AppAgentX: Evolving GUI Agents as Proficient Smartphone Users](https://mlsanity.com/paper/2503.02268/) (2025)
- [UFO2: The Desktop AgentOS](https://mlsanity.com/paper/2504.14603/) (2025)
- [API Agents vs. GUI Agents: Divergence and Convergence](https://mlsanity.com/paper/2503.11069/) (2025)
- [WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting Point](https://mlsanity.com/paper/2502.08047/) (2025)
- [Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures](https://mlsanity.com/paper/2604.03515/) (2026)
- [AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents](https://mlsanity.com/paper/2409.17140/) (2024)
- [The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation](https://mlsanity.com/paper/2607.22585/) (2026)
- [MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents](https://mlsanity.com/paper/2509.06477/) (2025)
- [A Framework for Testing and Adapting REST APIs as LLM Tools](https://mlsanity.com/paper/2504.15546/) (2025)
- [Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey](https://mlsanity.com/paper/2601.11655/) (2026)
- [OpenComputer: Verifiable Software Worlds for Computer-Use Agents](https://mlsanity.com/paper/2605.19769/) (2026)
- [CLI-Anything: Towards Agent-Native Computer Use](https://mlsanity.com/paper/2606.03854/) (2026)
- [Schema First Tool APIs for LLM Agents: A Controlled Study of Tool Misuse, Recovery, and Budgeted Performance](https://mlsanity.com/paper/2603.13404/) (2026)
- [Doc2Agent: Scalable Generation of Tool-Using Agents from API Documentation](https://mlsanity.com/paper/2506.19998/) (2025)
- [Automated Creation and Enrichment Framework for Improved Invocation of Enterprise APIs as Tools](https://mlsanity.com/paper/2509.11626/) (2025)
- [GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents](https://mlsanity.com/paper/2606.24551/) (2026)
- [From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents](https://mlsanity.com/paper/2510.04607/) (2025)
- [Terminal Is All You Need: Design Properties for Human-AI Agent Collaboration](https://mlsanity.com/paper/2603.10664/) (2026)
- [Tool Attention Is All You Need: Dynamic Tool Gating and Lazy Schema Loading for Eliminating the MCP/Tools Tax in Scalable Agentic Workflows](https://mlsanity.com/paper/2604.21816/) (2026)
- [E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios](https://mlsanity.com/paper/2607.23722/) (2026)

## Abstract (arXiv)

Large language model agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were designed for human end users or application developers, leaving agents to interpret visual controls or discover and compose low-level software operations. This mismatch can hinder even capable agents, yet it remains unclear what interface properties make desktop software easier for agents to use. To study this question, we treat software evolution as a natural source of interface variation and introduce DeskIF-Bench, a benchmark of 255 artifact-verified tasks across six desktop applications. By holding the task, agent, and verifier fixed while varying the software release, we measure how interface changes affect agent performance. Across two models and six applications, the newest release consistently outperforms the oldest. Trajectory analysis identifies three relevant interface properties: discoverability, granularity, and observability. Guided by these properties, we develop ANIS, a framework that synthesizes agent-native interfaces from the capabilities of installed applications. On an expanded evaluation of 368 tasks across eight applications, atomic interfaces improve success over native SDK use by 3.8 and 3.5 percentage points with DeepSeek V4 Flash and Claude Haiku 4.5, respectively, while reducing online token usage by approximately 73%. Goal-level commands further raise success to 74.5% and 67.4%, respectively.