让AI学会按需求生成专业幻灯片，靠逆向还原意图来评估质量。
Learning to Present: Inverse Specification Rewards for Agentic Slide Generation
- 用逆向任务让LLM从幻灯片反推原始需求，自动打分。
- 70亿参数模型在业务简报上达专家水平的91.2%。
- 工具调用和指令遵循比模型大小更重要，适合研究智能代理。
自动化幻灯片生成仍面临内容连贯性、视觉设计与受众感知的挑战。本文提出一个兼容OpenEnv的强化学习环境，使大语言模型（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。我们设计了多组件奖励系统，包括结构验证、渲染质量评估、基于LLM的美学评分、内容质量指标，以及一种逆向规范奖励——让另一LLM尝试从生成的幻灯片中恢复原始要求。该逆向任务提供整体质量信号。我们基于专家示范（使用Claude Opus 4.6收集）微调Qwen2.5-Coder-7B，仅更新0.5%参数，采用GRPO训练。在6个模型、48份多样化商业简报上的实验表明，微调后的7B模型达到基线模型33.1%的提升，并达到Claude Opus 4.6 91.2%的质量。六模型对比显示，指令遵循与工具使用合规性比参数量更能决定智能体表现。我们公开发布SlideRL数据集，包含288条多轮交互轨迹：https://huggingface.co/datasets/KarthikRagunathAnandaKumar/sliderl-multi-turn-rollouts，代码开源：https://github.com/pushing-the-frontier/slide-forge-llm
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。