paper-with-me

Papers

CogEvol: Towards Efficient and Reliable Learning Environment Generation

2026-08-31 · Shangqing Tu, Daniel Zhang-Li, Yucheng Wang, Shiyu Gan, Yanpeng Wang, Huiqiang Rong, Mofei Chen, Shen Yang, Yini Chen, Yinuo Duan, Haoxuan Li, Binglin Liu, Ye He, Danqi Zheng, Zhanxin Hao, Yuxuan Wu, Mengting Tao, Yuqiu Liu, Jifan Yu, Juanzi Li, Bin Xu, Lei Hou, Huiqin Liu, Yu Zhang hf

We present CogEvol, a family of models trained specifically for Learning Environment Generation: turning a course brief into a finished learning artifact (structured-JSON slides or self-contained interactive HTML pages) in a single pass. Across 220k production requests, CogEvol completes a slide in a median of 17 seconds and an interactive page in 59, replacing minutes-long multi-turn agent scaffolding. Reliability is enforced rather than hoped for: a production-grounded data pipeline turns real failures into 53,687 verified SFT samples, and a hybrid rule-plus-VLM reward drives GRPO-based RL, hardened after we caught and fixed a reward-hacking episode that produced visually convincing but unplayable games. CogEvol-27B scores 83.7 on slide quality and 63.7 on a 500-case interactive-HTML benchmark with 26.9x fewer parameters than flagship coding models, and, in collaboration with the OpenMAIC team, serves their live production traffic. CogEvol-4B is released openly under the Apache 2.0 license at https://github.com/CogEvol/CogEvol-4B; external flagships are measured on the same suites under the identical harness. Scaffold editing cuts interactive-page generation cost by a further ~76%, and the full stack runs on domestic Ascend accelerators at application-level parity with A800 GPUs, lowering the unit cost of AI-native education at scale.

📄 PDF Abstract BibTeX arXiv:2608.30968

Code (6)

CogEvol/CogEvol-4B ★ 30
Tavish9/awesome-daily-AI-arxiv ★ 114
Valiant-Cat/hfpaper
🤗 CogEvol/CogEvol-4B ★ 16
🤗 CogEvol/CogEvol-4B-Q4_K_M-GGUF ★ 2
🤗 prithivMLmods/CogEvol-4B-GGUF ★ 1

Similar Papers 제목 키워드 기반

CogEvolution: A Human-like Generative Educational Agent to Simulate Student's Cognitive Evolution

2026-04-16 · Wei Zhang, Yihang Cheng, Zhirong Ye, Kezhen Huang arxiv

Generative Agents, owing to their precise modeling and simulation capabilities of human behavior, have become a pivotal tool in the field of Artificial Intelligence in Education (AIEd) for uncovering complex cognitive pr…

AeroGrab: A Unified Framework for Aerial Grasping in Cluttered Environments

2026-03-16 · Shivansh Pratap Singh, Naveen Sudheer Nair, Samaksh Ujjawal, Sarthak Mishra 외 arxiv

Reliable aerial grasping in cluttered environments remains challenging due to occlusions and collision risks. Existing aerial manipulation pipelines largely rely on centroid-based grasping and lack integration between th…

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

2026-02-10 · Zhaoyang Wang, Canwen Xu, Boyi Liu, Yite Wang 외 arxiv

Recent advances in large language model (LLM) have empowered autonomous agents to perform multi-turn interactions with tools and environments. However, scaling such agent training is limited by the lack of diverse and re…

Reinforcement Learning

app.build: A Production Framework for Scaling Agentic Prompt-to-App Generation with Environment Scaffolding

2025-09-03 · Evgenii Kniazev, Arseny Kravchenko, Igor Rekun, James Broadhead 외 arxiv

We present app.build (https://github.com/neondatabase/appdotbuild-agent), an open-source framework that improves LLM-based application generation through systematic validation and structured environments. Our approach co…

Depth Completion in Unseen Field Robotics Environments Using Extremely Sparse Depth Measurements

2026-02-03 · Marco Job, Thomas Stastny, Eleni Kelasidi, Roland Siegwart 외 arxiv

Autonomous field robots operating in unstructured environments require robust perception to ensure safe and reliable operations. Recent advances in monocular depth estimation have demonstrated the potential of low-cost c…

Monocular Depth EstimationDepth Completion