When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis

Computer Science > Artificial Intelligence [Submitted on 17 Apr 2026] When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis Justice Owusu Agyemang, Michael Agyare, Miriam Kobbinah, Nathaniel Agbugblah, Prosper Addo LLM-powered coding agents suffer from a poorly understood failure mode we term output stalling: the agent silently produces empty responses when attempting to generate large, format-heavy documents. We present a theoretical framework that explains and prevents this failure through three contributions. (1) We introduce Output Generation Capacity (OGC), a formal measure of an agent's effective ability to produce output given its current context state - distinct from and empirically smaller than the raw context window. (2) We prove a Format-Cost Separation Theorem showing that deferred template rendering is always at least as token-efficient as direct generation for any format with overhead multiplier \mu_f > 1, and derive tight bounds on the savings. (3) We formalize Adaptive Strategy Selection, a decision framework that maps the ratio of estimated output cost to available OGC into an optimal generation strategy (direct, chunked, or deferred). We validate the theory through controlled experiments across three models (Claude 3.5 Sonnet, GPT-4o, Llama 3.1 70B), four document types, and an ablation study isolating each component's contribution. Deferred rendering reduces LLM generation tokens by 48-72% across all conditions and eliminates output stalling entirely. We instantiate the framework as GEN-PILOT, an open-source MCP server, demonstrating that the theory translates directly into a practical tool. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.16736 [cs.AI]   (or arXiv:2604.16736v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.16736 Focus to learn more Submission history From: Justice Owusu Agyemang [view email] [v1] Fri, 17 Apr 2026 22:48:23 UTC (20 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)