From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts
- URL: http://arxiv.org/abs/2609.17326v1
- Date: Tue, 15 Sep 2026 15:32:07 GMT
- Title: From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts
- Abstract summary: PosterVisor is a control framework that shifts poster generation from transient prompts to persistent control.<n>An Orchestrator grounds rubrics in the paper and visual assets, compiling them into a Semantic-Geometric Contract.<n>Recursive Contract Enforcement (RCE) dynamically triggers checks across stages as evidence emerges.
- Score: 67.34566880931716
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Scientific poster generation distills a multimodal paper into a single-page visual artifact, forcing strict trade-offs between informational coverage and readability under a fixed spatial budget. Existing methods pass plans as transient prompts and validate individual stages in isolation. This strategy causes requirements to drift across content and layout modules, and previous checks to be silently invalidated. We introduce PosterVisor, a control framework that shifts poster generation from transient prompts to persistent control. An Orchestrator grounds rubrics in the paper and visual assets, compiling them into a Semantic-Geometric Contract (SGC) that binds claims and sources to required visuals, budgets, and spatial commitments. Only fully instantiated records become executable assertions; other usable requirements remain soft guidance. Recursive Contract Enforcement (RCE) dynamically triggers checks across stages as evidence emerges. Crucially, during repairs, RCE rechecks affected checkpoint states, preventing repair-induced regressions from propagating silently. We instantiate PosterVisor in HTML/CSS and editable PPTX generators. On the 100-paper Paper2Poster benchmark, PosterVisor-PPT improves observed mean poster-grounded QA accuracy over PosterGen (64.47% vs. 58.53%) and is preferred by human judges in 72.5% of non-tied pairwise comparisons (95% CI, 61.6-83.4%). A secondary 30-paper study also yields higher VLM Overall and PaperQuiz means. These results support rubric-compiled contracts and stage-conditioned enforcement for controllable poster synthesis.
Related papers
- TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents [54.88208747581851]
Training-free visual token pruning can reduce this cost, but cache reuse introduces a fundamental constraint.<n>We propose textbfmethod, a training-free framework for emphtextbfTrajectory-textbfrobust textbfAdmission and textbfCoverage-aware textbfEvidence ordering.
arXiv Detail & Related papers (2026-09-09T15:12:48Z) - Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework [49.16055123488827]
coding agents powered by large language models can now generate code patches directly from bug reports.<n>No mechanism independently verifies whether it truly resolves the reported problem.<n>We propose RETRACE, a training-free post-generation verification framework.
arXiv Detail & Related papers (2026-08-09T22:59:13Z) - PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs [34.40233517054039]
PosterMELD is a template-conditioned multi-agent pipeline.<n>Each request exports editable PowerPoint (PPTX) and Portable Network Graphics (PNG) artifacts.<n>Native editability and explicit design controls are retained at a mean cost of USD0.38 per request, 3.5% of Codex+Skill's.
arXiv Detail & Related papers (2026-08-03T13:39:25Z) - Context Assembly as the Controlled Variable: A Control-Theoretic View of Harness Policies for Frozen LLM Agents [2.452218069720666]
We do not claim to introduce control theory to LLM agents -- that ship has sailed.<n>Prior work controls tool selection, inter-agent message routing, or the agent's raw action stream.<n>This paper develops the formal decomposition of the online controller.
arXiv Detail & Related papers (2026-07-28T08:07:06Z) - TRACE-CTI: Auditable Post-Extraction Governance of TTP Claims with Knowledge Graphs [4.960649631468518]
TRACE-CTI is a post-extraction claim-governance framework.<n>It aggregates run-level Predictions into configuration-level GraphAssertions.<n>It materializes setup-deduplicated corroboration as ConsensusAssertions.
arXiv Detail & Related papers (2026-07-27T15:33:18Z) - PosterHarness: Turning Scientific Poster Generation into an Auditable Instruction-Following Benchmark [7.957250777212916]
Text-rich image models can now design poster-scale layouts, but we lack ways to measure whether they honor scientific communication contracts.<n>We present POSTERHARNESS, an auditable harness reframing poster generation as measurable instruction-following tasks.
arXiv Detail & Related papers (2026-07-03T06:39:56Z) - Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering [54.97384993676565]
We formalize Regulatory Compliance QA with RegOps-Bench, a novel benchmark featuring an Operational Knowledge Graph derived from complex national R&D regulations.<n>RefWalk traverses cross-document citations, fuses multi-view candidates via max-based aggregation, and enforces per-rule attribution to explicitly map claims to sources.
arXiv Detail & Related papers (2026-05-28T10:38:38Z) - Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy [51.887915969023965]
We show that modern Large Language Models (LLMs) undergo alignment, leaving a measurable distributional imprint.<n>To mitigate the instability in high-entropy regions, we introduce Log-likelihood Alignment Preference Discrepancy (LAPD)<n>LAPD is a standardized information-weighted statistic based on alignment imprint.
arXiv Detail & Related papers (2026-04-18T09:12:24Z) - PPTArena: A Benchmark for Agentic PowerPoint Editing [57.55409966131844]
We introduce a benchmark for PowerPoint editing that measures reliable modifications to real slides under natural-language instructions.<n>PPTArena focuses on in-place editing across 100 decks, 2125 slides, and over 800 targeted edits covering text, charts, tables, animations, and master-level styles.<n>We propose a structure-aware slide-editing agent that plans semantic edit sequences, routes between high-level programmatic tools, and deterministic XML operations for precise control.
arXiv Detail & Related papers (2025-12-02T18:59:50Z) - Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers [34.9495497884296]
Poster generation is a crucial yet challenging task in scientific communication.<n>We introduce the first benchmark and metric suite for poster generation.<n>PosterAgent is a top-down, visual-in-the-loop multi-agent pipeline.
arXiv Detail & Related papers (2025-05-27T17:58:49Z)
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.