cs.CLNov 16, 2026

Edit Recommendation: Can LLMs Anticipate Edit Requests from Users, and When?

Authors: Daisuke Kikuta

Organizations: NTT, Inc.

Abstract

After a large language model (LLM) agent generates an artifact, users often send edit requests for it. This paper studies whether an LLM can anticipate these requests before they are sent. Such anticipation is useful in practice because it reduces the effort of user review and feedback. We formalize this task as edit recommendation and build EditRecBench, a benchmark for evaluating the performance of LLMs on this task, from real-world conversation logs in WildChat-4.8M. Through benchmarking and failure analysis, we identify a practical challenge that some cases are inherently difficult to predict in real-world settings. To address this, we introduce decision model-based gating to filter out cases where predictions are unlikely to be correct before they are presented to the user. Our trained model outperforms existing decision models and raises pass@5 among shown suggestions by 12--25 points at a gating threshold. Our code is available at https://github.com/ntt-dkiku/llm-edit-recommendation.

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Generating Edit-Inducing Questions for AI Research Manuscripts

    Sep 29, 2026Sebastian Joseph, Zichao Wang, Jennifer Healey +3Text GenerationLanguage Model Generation Evaluation

  2. Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)

    Mar 18, 2026Zichen Tang, Zirui Zhang, Qian Wang +3Large Language Model-Based RecommendationLLM Agent Reliability

  3. Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning

    Apr 14, 2026Timon Ziegenbein, Maja Stahl, Henning WachsmuthLanguage Model EditingRL for Language Models