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

Arabic

يتم استخدام نموذج إنتاج الكود بشكل متزايد لإنتاج الأدوات التفاعلية، مثل المواقع الإلكترونية والمواقع المستخدمة. تستخدم العديد من الخصائص التي تحدد ما إذا كانت هذه المواقع مفيدة فقط من خلال التفاعل الإيجابي، مما يجعلها صعوبة في إدماجها في تدريب نموذج. في هذه المقالة، نحن نقدم RELIEF (تقييم بناء على التعلم من تجربة التفاعلية والتفاعلات)، طريقة لتعزيز نموذج إنتاج الكود باستخدام التعليقات على المواقع التي تم إنشاؤها. يستخدم RELIEF آلة تشفير لتقييم هذه المواقع، ثم يتم دمج التغييرات في أدوات إنشاء نموذج إنشاء الأدوات الأصلية الأصلية. لتقييم

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26636, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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