Reviser: Writing and Editing Text with Autoregressive Cursor Actions

arXiv:2609.20830 · cs.CL · Submitted 2026-07-23 · Read on arXiv

cs.CL

Submitted: 2026-07-23

Updated: 2026-10-14

Comments: 45 pages, 2 figures. Code: https://github.com/Sean-Diab/Reviser Checkpoints: https://huggingface.co/sean-diab/reviser-checkpoints

Code: https://github.com/Sean-Diab/Reviser

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster
• Proximal Policy Optimization Algorithms
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• Dream 7B: Diffusion Large Language Models
• OPT: Open Pre-trained Transformer Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering