arXiv:2601. 04203v2 Announce Type: replace-cross Abstract: We present FronTalk, a benchmark for front-end code generation that pioneers the study of a unique interaction dynamic: conversational code generation with multi-modal feedback.
Generating HTML from natural-language specifications is an important application of code large language models (LLMs). Despite producing renderable pages, current models often fail to ensure functiona...
arXiv:2608. 10319v1 Announce Type: cross Abstract: Large language model (LLM)-powered agents have rapidly evolved from code-completion tools into solvers of complex software engineering tasks.
The paper investigates whether tailoring coding agent skills to individual developers improves collaboration. It introduces a framework that bootstraps rule‑based skills and refines them with LLMs to capture developer‑specific preferences, and evaluates this approach using an interactive replay system with a simulated developer. Experiments on real interaction logs show that while task‑specific skills generally perform best, personalized skills become more effective when developers frequently express consistent preferences, especially on related tasks.
The paper argues that user feedback from real interactions is a valuable learning signal for Large Language Models (LLMs), contrary to recent claims that it is too noisy to use. By creating synthetic data with a clear ground truth and testing on naturalistic data, the authors show that revisions guided by user feedback fix targeted issues more often than baseline revisions. They further reveal that current evaluation methods bias against feedback‑driven improvements, as judges tend to overlook genuinely corrected responses and favor inferior baselines.
SWE-Journey is a new benchmark designed to evaluate coding assistants in more realistic settings, focusing on long-horizon tasks and multi-turn interactions. It introduces a weak-to-strong synthesis pipeline to create extended coding challenges and a user-simulation agent based on four real user personas to mimic authentic code-assistance dialogues. The benchmark reveals that while models succeed on over 75% of tests with software architects, they manage less than 25% with non-coders, highlighting a significant gap in current assistant capabilities.
arXiv:2606. 00154v1 Announce Type: cross Abstract: Recent advancements in multimodal large language models (MLLMs) have achieved remarkable progress in multimodal reasoning and code generation, catalyzing a new paradigm for front-end development.
RILA is an execution‑driven agent that integrates browser rendering into the generation loop for interactive web development. It uses an Action Interaction Verification module to replay reference interactions on generated pages, collecting execution‑aware observations, and an Execution‑aware Rendering Score to jointly assess interaction correctness and visual fidelity during iterative optimization. A data synthesis pipeline further augments training data, enabling RILA to significantly improve interaction and visual quality across foundation models, even outperforming larger one‑shot generators.
arXiv:2507. 22080v2 Announce Type: replace-cross Abstract: Acquiring high-quality instruction-code pairs is essential for training Large Language Models for code generation.
arXiv:2507.12674v3 Announce Type: replace-cross Abstract: Evaluating Artificial Intelligence (AI) tutor feedback before deployment requires anticipating student engagement, typically assessed through...
arXiv:2608.29889v1 Announce Type: new Abstract: Programming with AI is increasingly agentic, users prompt LLMs to directly edit their code and review the changes, with adoption growing especially for...
arXiv:2608. 03689v1 Announce Type: new Abstract: Large language models are increasingly capable of synthesizing executable frontend projects, yet existing benchmarks still treat web generation as a static evaluation problem.