The Last Mile Is the File: OfficeEditBench for Preservation-Aware Office Editing

arXiv:2609.34469 · cs.SE, cs.CL · Submitted 2026-09-28 · Read on arXiv

cs.SE, cs.CL

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/Aniriswu/OfficeEditBench

Terminology

• Benchmark — 28× in this paper · explained in 2 episodes
• Verifier — 22× in this paper · explained in 2 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Provenance — 3× in this paper · explained in 4 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks
• Datasheets for Datasets
• PPTArena: A Benchmark for PowerPoint Editing
• OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation
• OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
• SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties