学习呈现：用于代理幻灯片生成的逆规范奖励
Learning to Present: Inverse Specification Rewards for Agentic Slide Generation
AI总结：
本文提出一个兼容OpenEnv的强化学习环境，通过工具使用训练LLM代理生成专业HTML幻灯片，引入多组件奖励系统，包括结构验证、渲染质量评估、LLM审美评分、内容质量指标和逆规范奖励，实验显示细调模型在质量与工具使用合规性上表现优异。
摘要：
自动化演示生成仍是一个具有挑战性的任务，需要连贯的内容创建、视觉设计和观众意识的沟通。本文提出一个兼容OpenEnv的强化学习环境，其中LLM代理通过工具使用学习研究主题、规划内容并生成专业HTML幻灯片。我们引入一个多组件奖励系统，结合结构验证、渲染质量评估、基于LLM的审美评分、内容质量指标和一个逆规范奖励，该奖励衡量生成幻灯片多大程度上忠实传达其预期目的。逆规范奖励是一种“逆任务”，其中LLM尝试从生成的幻灯片中恢复原始规范，提供全面的质量信号。我们的方法通过GRPO微调Qwen2.5-Coder-7B，仅在从专家演示中收集的提示上训练0.5%的参数。在48个多样化的商业简报上进行实验，显示我们的微调7B模型在质量上达到Claude Opus 4.6的91.2%，同时比基线模型提升33.1%。六个模型的比较表明，指令遵循和工具使用合规性，而非原始参数数量，决定了代理任务性能。我们贡献了SlideRL，一个包含288个多轮滚动轨迹的开源数据集，涵盖所有六个模型：https://huggingface.co/datasets/KarthikRagunathAnandaKumar/sliderl-multi-turn-rollouts 代码：https://github.com/pushing-the-frontier/slide-forge-llm
英文摘要：
Automated presentation generation remains a challenging task requiring coherent content creation, visual design, and audience-aware communication. 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. 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. The inverse specification reward, an "inverse task" where an LLM attempts to recover the original specification from generated slides, provides a holistic quality signal. Our approach fine-tunes Qwen2.5-Coder-7B via GRPO, training only 0.5% of parameters on prompts derived from expert demonstrations collected using Claude Opus 4.6. 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. The six-model comparison reveals that instruction adherence and tool-use compliance, rather than raw parameter count, determine agentic task performance. We contribute SlideRL, an open-source dataset of 288 multi-turn rollout trajectories across all six models: https://huggingface.co/datasets/KarthikRagunathAnandaKumar/sliderl-multi-turn-rollouts Code: https://github.com/pushing-the-frontier/slide-forge-llm
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
