# ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks

arXiv: https://arxiv.org/abs/2606.21654 · HTML: https://mlsanity.com/paper/2606.21654/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 19 Jun 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, 14 of 14)

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis](https://mlsanity.com/paper/2412.19723/) (2024)
- [AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials](https://mlsanity.com/paper/2412.09605/) (2024)
- [WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks](https://mlsanity.com/paper/2407.05291/) (2024)
- [Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents](https://mlsanity.com/paper/2502.11357/) (2025)
- [NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild](https://mlsanity.com/paper/2410.02907/) (2024)
- [OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows](https://mlsanity.com/paper/2508.09124/) (2025)
- [AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents](https://mlsanity.com/paper/2506.14205/) (2025)
- [Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale](https://mlsanity.com/paper/2409.15637/) (2024)
- [GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks](https://mlsanity.com/paper/2509.23738/) (2025)
- [Efficient Agent Training for Computer Use](https://mlsanity.com/paper/2505.13909/) (2025)
- [Agent-as-a-Judge](https://mlsanity.com/paper/2601.05111/) (2026)

## Built on by (most cited first, 1 of 1)

- [OSWorld-Pro: Process-based Evaluation for Computer Use Agents](https://mlsanity.com/paper/2609.24890/) (2026)

## Abstract (arXiv)

Computer use agents are evaluated almost exclusively on atomic desktop tasks, but realistic desktop work requires sustaining state across multiple objectives. We study this gap with ChainWorld, which composes atomic OSWorld tasks into long horizon desktop workloads through directional compatibility search while preserving the source evaluators. The resulting workload contains 347 chains of length two to four and compares two renderings of the same task sequence. In single turn evaluation, all tasks are presented together in one prompt. In multi turn evaluation, tasks are revealed one at a time. Across four current computer use agents, maximum chain completion is 31%. Multi turn evaluation improves completion for three models, but both protocols remain challenging. The two protocols also expose different failure profiles. Single turn failures concentrate on artifact precision, while multi turn failures more often reflect session management problems such as fragmented progress and later turn disengagement.