CogEvol: Towards Efficient and Reliable Learning Environment Generation

• URL: http://arxiv.org/abs/2608.30968v2
• Date: Wed, 02 Sep 2026 05:30:12 GMT
• Title: CogEvol: Towards Efficient and Reliable Learning Environment Generation
• Abstract summary: We present CogEvol, a family of models trained specifically for Learning Environment Generation.<n>CogEvol completes a slide in a median of 17 seconds and an interactive page in 59, replacing minutes-long multi-turn agent scaffolding.<n>A production-grounded data pipeline turns real failures into 53,687 verified SFT samples.
• Score: 49.18054685846454
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation [53.851483224691634]
  We present a large-scale synthetic data production pipeline built on Unreal Engine for generating action-conditioned, multi-view video.<n>The pipeline has produced 2,691 hours of 1080p video and 6,076 hours of 720p video.
  arXiv  Detail & Related papers  (2026-09-03T08:58:04Z)
• From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix [55.08143827481755]
  We consolidate traffic from over 200 internal applications onto a single model.<n>We train a separate GRPO expert per axis and merge them via two-stage SLERP.<n>The model absorbs 50% of platform traffic, 116M requests per month, at a fraction of the serving cost.
  arXiv  Detail & Related papers  (2026-09-01T17:39:26Z)
• EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants [10.510136510866099]
  Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests evolve.<n>We introduce EvoGenUI-Bench, a benchmark for multi-turn interface maintenance comprising 150 five-turn tasks and 750 turns across three scenarios.<n>We execute generated artifacts in a browser and evaluate them using screenshots, source and DOM evidence, actor traces, and runtime logs.
  arXiv  Detail & Related papers  (2026-08-29T17:54:02Z)
• Dual-Node NVIDIA DGX Spark over Tailscale: A Remote-Access Testbed for Distributed LLM Training and Cyber-Threat-Intelligence Fine-Tuning [0.0]
  This report presents a proof-of-concept deployment of distributed NanoChat pretraining across two NVIDIA DGX Spark systems.<n>The cluster supports a 400-level AI course (CS 426) and a query engine for Security+ POGIL activities in CBS 255.
  arXiv  Detail & Related papers  (2026-08-07T13:41:57Z)
• LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation [53.88286427894783]
  Vision Language Models (VLMs) have emerged in the robotic domain as a powerful tool that enables environmental perception with language context.<n>Yet, their computational footprint typically confines them to cloud execution, hindering low-latency inference with local deployment on resource-constrained robots.<n>We present a distillation strategy that transfers complex spatial-semantic reasoning from large frontier models into a lightweight, 4B- parameter local VLM for edge execution on embedded GPU devices.
  arXiv  Detail & Related papers  (2026-06-26T09:11:59Z)
• ProCUA-SFT Technical Report [80.97543110323542]
  Training computer-use agents (CUAs) requires large-scale, diverse trajectory data collected in full desktop environments.<n>We present ProCUA-SFT, a dataset of 3.1M step-level SFT samples distilled from 93K synthetic trajectories.<n>Fine-tuning UI-TARS 7B on ProCUA-SFT for one epoch yields 45.0% on OSWorld -- an 18.7 percentage-point improvement over the base model.
  arXiv  Detail & Related papers  (2026-06-15T22:04:11Z)
• HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools [2.0320563270126493]
  We present HyDRA, a framework that predicts fine-grained, multi-dimensional capability requirements per query.<n>A shortfall-matching algorithm then selects the cheapest model whose capabilities meet the predicted requirements.<n>The framework is deployed to all users in GitHub Copilot's VS Code Chat auto-mode.
  arXiv  Detail & Related papers  (2026-05-16T18:19:30Z)
• Orchard: An Open-Source Agentic Modeling Framework [124.68499958175111]
  We present Orchard, an open-source framework for scalable agentic modeling.<n>At its core is Orchard Env, a lightweight environment service providing reusable primitives for sandbox lifecycle management.<n>On top of Orchard Env, we build three agentic modeling recipes.
  arXiv  Detail & Related papers  (2026-05-14T16:35:12Z)
• WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation [88.10947115397971]
  This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories.<n>Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls.<n> Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification.
  arXiv  Detail & Related papers  (2026-05-11T17:49:43Z)
• Learning to Present: Inverse Specification Rewards for Agentic Slide Generation [15.152850806890065]
  This work proposes an OpenEnv-compatible reinforcement learning environment where LLM agents learn to research topics, plan content, and generate professional HTML slide presentations through tool use.<n>We introduce a multi-component reward system combining structural validation, render quality assessment, LLM-based aesthetic scoring, content quality metrics, and an inverse specification reward that measures how faithfully generated slides convey their intended purpose.<n> Experiments on 48 diverse business briefs across six models demonstrate that our fine-tuned 7B model achieves 91.2% of Claude Opus 4.6's quality while improving 33.1% over the base model.
  arXiv  Detail & Related papers  (2026-03-17T17:45:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.