We present RAGthoven, our system for SemEval-2026 Task 1 (MWAHAHA), Subtask A (multilingual constrained humor generation in English, Spanish, and Chinese). RAGthoven decomposes creative text generation into a multi-stage large language model (LLM) pipeline, consisting of Planner, Best-of-N Writer, Reflector for self-critique, and LLM-as-a-judge Judge. This system is grounded in computational humor theory (Benign Violation Theory, Script-based Semantic Theory of Humor) and refined through ten experiments. In our final configuration, we augment the Planner with retrieval-augmented generation (RAG) from a curated joke corpus, seeding generation with diverse joke mechanisms. We also evaluate two agentic variants—ReAct-style sequential tool-calling (Exp09) and autonomous multi-branch orchestration (Exp10)—that expose the same four stages with a deterministic ConstraintAudit checker. Across four frontier models on a held-out 12-instance English sample, neither agentic variant produced outputs we judged superior to the non-agentic pipeline despite substantially higher tool-call budgets. RAGthoven shares Rank 1 with the Gemini 2.5 Flash baseline in all three languages, with overlapping organizer-reported confidence intervals. In Spanish, it leads the baseline by 42 raw Elo points (1182 vs. 1140), while in English (1045 vs. 1081) and Chinese (1045 vs. 1053) the baseline holds the higher raw rating within the same statistical tie. Together, these results suggest language-dependent diminishing returns from elaborate multi-stage prompt engineering and agentic scaffolding once a strong frontier model is in the loop.
Blogger's Review: RAGthoven's multi-stage pipeline showcases potential in the humor generation field, although the complexity of the architecture does not seem to yield significant advantages in the presence of strong models. This suggests a need to balance complexity with actual effectiveness when designing generative systems, especially in multilingual contexts. Understanding the computational theories of humor is also crucial for enhancing generation quality.