Learning to Present: Inverse Specification Rewards for Agentic Slide Generation

• URL: http://arxiv.org/abs/2603.16839v1
• Date: Tue, 17 Mar 2026 17:45:53 GMT
• Title: Learning to Present: Inverse Specification Rewards for Agentic Slide Generation
• Abstract summary: 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.
• Score: 15.152850806890065
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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

Related papers

• Can LLMs Learn and Apply Multi-Level Modelling Semantics? A First Empirical Study [2.9612857576788447]
  Multi-level modelling (MLM) can directly represent three or more abstraction levels, but this comes at the cost of more complex semantic constraints that model correctness depends on.<n>This paper presents the first empirical study of this question.
  arXiv  Detail & Related papers  (2026-07-14T20:41:43Z)
• 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)
• AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards [25.706853645118453]
  AeSlides is a reinforcement learning framework with verifiable rewards for Aesthetic layout supervision in Slide generation.<n>With only 5K training prompts on GLM-4.7-Flash, AeSlides improves aspect ratio compliance from 36% to 85%, while reducing whitespace by 44%, element collisions by 43%, and visual imbalance by 28%.
  arXiv  Detail & Related papers  (2026-04-21T11:59:03Z)
• MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images [8.327738094483207]
  Lifelong learning on Whole Slide Images (WSIs) aims to train or fine-tune a unified model sequentially on cancer-related tasks.<n>We introduce MergeSlide, a framework that treats lifelong learning as a model merging problem by leveraging a vision-language pathology model.
  arXiv  Detail & Related papers  (2025-11-17T07:51:18Z)
• AutoPresent: Designing Structured Visuals from Scratch [99.766901203884]
  We benchmark end-to-end image generation and program generation methods with a variety of models.<n>We create AutoPresent, an 8B Llama-based model trained on 7k pairs of instructions paired with code for slide generation.
  arXiv  Detail & Related papers  (2025-01-01T18:09:32Z)
• Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration [90.41908331897639]
  Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data. We present a novel approach, ReverseGen, designed to automatically generate effective training samples.
  arXiv  Detail & Related papers  (2024-10-22T06:43:28Z)
• What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices [91.71951459594074]
  Long language models (LLMs) with extended context windows have significantly improved tasks such as information extraction, question answering, and complex planning scenarios.<n>Existing methods typically utilize the Self-Instruct framework to generate instruction tuning data for better long context capability improvement.<n>We propose the Multi-agent Interactive Multi-hop Generation framework, incorporating a Quality Verification Agent, a Single-hop Question Generation Agent, a Multiple Question Sampling Strategy, and a Multi-hop Question Merger Agent.<n>Our findings show that our synthetic high-quality long-context instruction data significantly enhances model performance, even surpassing models trained on larger amounts of human
  arXiv  Detail & Related papers  (2024-09-03T13:30:00Z)
• Proofread: Fixes All Errors with One Tap [14.785502657069902]
  This paper demonstrates Proofread, a novel Gboard feature powered by a server-side Large Language Models (LLMs) in Gboard. We describe the complete system in this paper, from data generation, metrics design to model tuning and deployment.
  arXiv  Detail & Related papers  (2024-06-06T21:38:08Z)
• Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs [49.88461345825586]
  This paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. We present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. We show that our model exhibits a 5.2% accuracy improvement over Qwen-VL and surpasses the accuracy of Kosmos-2 by 24.7%.
  arXiv  Detail & Related papers  (2023-10-01T05:53:15Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)

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.