Yes FLoReNce, I Will Do Better Next Time! Agentic Feedback Reasoning for Humorous Meme Detection

TL;DR

This paper introduces FLoReNce, a novel agentic feedback reasoning framework that enhances AI's ability to understand and explain humorous memes by integrating critique and feedback in a closed-loop during learning and using this knowledge during inference.

Contribution

FLoReNce is the first framework to combine agentic feedback with a non-parametric knowledge base for improved meme humor detection and explanation without finetuning.

Findings

Improves predictive accuracy on PrideMM dataset

Enhances explanation quality for humor detection

Demonstrates effectiveness of feedback-regulated prompting

Abstract

Humorous memes blend visual and textual cues to convey irony, satire, or social commentary, posing unique challenges for AI systems that must interpret intent rather than surface correlations. Existing multimodal or prompting-based models generate explanations for humor but operate in an open loop,lacking the ability to critique or refine their reasoning once a prediction is made. We propose FLoReNce, an agentic feedback reasoning framework that treats meme understanding as a closed-loop process during learning and an open-loop process during inference. In the closed loop, a reasoning agent is critiqued by a judge; the error and semantic feedback are converted into control signals and stored in a feedback-informed, non-parametric knowledge base. At inference, the model retrieves similar judged experiences from this KB and uses them to modulate its prompt, enabling better, self-aligned reasoning without finetuning. On the PrideMM dataset, FLoReNce improves both predictive performance and explanation quality over static multimodal baselines, showing that feedback-regulated prompting is a viable path to adaptive meme humor understanding.