paper-with-me

Papers

MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis

2026-07-29 · Yihao Chen, Shi Chang, Khaled Chawa, Feng Lin, Boyuan Chen, Shaowei Wang, Ahmed E. Hassan hf

Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation. However, constructing a complete program from scratch remains a major challenge: even the frontier models evaluated on ProgramBench fully resolve fewer than 1% of tasks. One obstacle is the lack of scalable training environments for this from-scratch setting, spanning the whole software engineering life cycle, as existing environment-construction frameworks focus only on a single phase in software development. To address this gap, we introduce MindForge, an automated pipeline that converts open-source command-line programs into source-free environments that expose only a compiled reference executable and its documentation. Using MindForge, we construct training environments from repositories disjoint from those in ProgramBench, and curate a high-quality data recipe consisting of program synthesis trajectories using GLM-5.2 as the teacher agent. Fine-tuning Qwen3.6-27B on these trajectories increases its ProgramBench average test pass rate from 37.98% to 49.51%, achieving performance comparable to substantially larger frontier models. Moreover, the fine-tuned model consistently improves over the base model across all seven unseen software engineering benchmarks, spanning long-horizon repository generation and translation, bug fixing, feature implementation, and cross-language issue resolution, with absolute gains of 31.00 points on RepoZero-C2Rust, 14.16 on DeepSWE, 10.70/4.56 on NL2Repo-Bench (with/without tests), 5.04 on SWE-bench Verified, 5.93 on SWE-bench Pro, 5.22 on SWE-bench Multilingual, and 4.94 on FeatBench.

📄 PDF Abstract BibTeX arXiv:2607.27146

Code (0)

등록된 구현이 없습니다.

Tasks

Program Synthesis

Similar Papers 제목 키워드 기반

MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Collaborative Learning

2024-11-20 · Mircea Lică, Ojas Shirekar, Baptiste Colle, Chirag Raman

Contemporary embodied agents, such as Voyager in Minecraft, have demonstrated promising capabilities in open-ended individual learning. However, when powered with open large language models (LLMs), these agents often str…

MinecraftTransfer Learning

A Whole-Person Function Dictionary for the Mobility, Self-Care and Domestic Life Domains: a Seedset Expansion Approach

2022-06-01 · LREC 2022 6 · Ayah Zirikly, Bart Desmet, Julia Porcino, Jonathan Camacho Maldonado 외

Whole-person functional limitations in the areas of mobility, self-care and domestic life affect a majority of individuals with disabilities. Detecting, recording and monitoring such limitations would benefit those indiv…

Mitigating belief projection in explainable artificial intelligence via Bayesian Teaching

2021-02-07 · Scott Cheng-Hsin Yang, Wai Keen Vong, Ravi B. Sojitra, Tomas Folke 외

State-of-the-art deep-learning systems use decision rules that are challenging for humans to model. Explainable AI (XAI) attempts to improve human understanding but rarely accounts for how people typically reason about u…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)image-classificationImage Classification

Meta-Teaching: Curriculum Generation for Lifelong Learning

2019-05-16 · ICML Workshop AMTL 2019 6 · Anonymous

Meta-learning will be crucial to creating lifelong, generalizable AI. In practice, however, it is hard to define the meta-training task distribution that is used to train meta-learners. If made too small, tasks are too s…

Lifelong learningMeta-Learning

SpatialAfford: Teaching Compact VLMs Where to Look and Where to Ground for Affordance

2026-08-01 · Yufei Zhang, Chenlu Zhan, Donghui Sun, Xiaoxin Chen 외 arxiv

Affordance grounding aims to localize the functional region for interaction, such as the handle to grasp or the button to press, rather than the whole object. This makes it more challenging than generic visual grounding …

Reinforcement LearningSpatial ReasoningVisual Grounding