Newest papers

Revision-Based Learning from Interactive Experience and Feedback

Jiawen Li, Chenming Ge, Alice Gao, Rishab Vempati, Yi-Hao Peng, Jason Wu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26636 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Model generasi kode semakin banyak digunakan untuk menghasilkan artefak interaktif, seperti situs web dan antarmuka pengguna. Banyak properti yang menentukan apakah antarmuka ini berguna hanya menjadi terlihat melalui interaksi realistis, membuatnya sulit untuk dimasukkan ke dalam pelatihan model. Dalam makalah ini, kami memperkenalkan RELIEF (Revision-based Learning from Interactive Experience and Feedback), sebuah metode untuk meningkatkan model generasi kode menggunakan umpan balik pada antarmuka yang dihasilkan. RELIEF menggunakan agen pengkodean untuk memodifikasi antarmuka ini, kemudian mengintegrasikan perbaikan ke dalam jejak generasi asli mereka untuk menghasilkan pengawasan untuk tuning halus. Untuk mengevaluasi RELIEF, kami mengumpulkan set data 200 yang dihasilkan secara sintetis dikombinasikan dengan 355 catatan interaksi situs web dan disertai umpan balik dari 24 pengguna. Kami menggunakan kritik yang

Machine translation (Meta M2M100); the English original follows.

Abstract

Code generation models are increasingly used to produce interactive artifacts, such as websites and user interfaces. Many properties that determine whether these interfaces are useful only become apparent through realistic interaction, making them difficult to incorporate into model training. In this paper, we introduce RELIEF (REvision-based Learning from Interactive Experience and Feedback), a method for improving code generation models using feedback on their generated interfaces. RELIEF uses a coding agent to revise these interfaces, then incorporates the improvements into their original generation traces to produce supervision for fine-tuning. To evaluate RELIEF, we collected a dataset of 200 synthetically generated websites paired with 355 interaction recordings and accompanying feedback from 24 users. We used critiques derived from code inspection, automated interaction, explicit human feedback, and human interaction recordings to fine-tune variants of two code generation models. Our results show that feedback effectiveness varies with base model capabilities, with critiques inferred from human interaction recordings leading to the largest usability improvements overall under our tested models.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Usability, Human–computer interaction, Code (set theory), Coding (social sciences), User experience design

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange