coding agents posts and papers

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself arxiv.org

CodeMidas builds RL environments directly from open‑source code: agents explore a repo, infer a spec, generate tests from the original implementation, and filter tasks via execution checks. The pipeline yields 5,545 high‑quality coding tasks across 23 languages and 15 domains. Training the MiMo‑V2.5 agent with GRPO on this dataset improves benchmark scores by 8‑18% (e.g., DeepSWE +11.7%, ProgramB…

Hugging Face Daily Papersarxiv.orgBowen Ye, Lei Li, Shicheng Li4d1 minpaper

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks arxiv.org

ProgramDistill is a new benchmark that automatically extracts 1,975 replay‑verified feature behaviors from 26 real web apps, builds 4,063 coding‑agent tasks, and measures how well state‑of‑the‑art agents (e.g., GPT‑6 Astra, Claude Opus 5) can reconstruct full or partial applications, revealing steep drops in success as restoration depth grows.

Hugging Face Daily Papersarxiv.orgJeonghye Kim, Minseon Kim, Young Jin Kim6d1 minpaper

coding agents

CodeMidas: Scaling Agentic Coding RL Environments from Code Itselfarxiv.org

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasksarxiv.org

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself arxiv.org

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks arxiv.org