# RAM-SD: Retrieval-Augmented Multi-agent framework for Sarcasm Detection

arXiv: https://arxiv.org/abs/2601.17002 · HTML: https://mlsanity.com/paper/2601.17002/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Creating and Characterizing a Diverse Corpus of Sarcasm in Dialogue](https://mlsanity.com/paper/1709.05404/) (2017)
- [Reasoning with Sarcasm by Reading In-between](https://mlsanity.com/paper/1805.02856/) (2018)
- [Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text](https://mlsanity.com/paper/1611.00472/) (2016)
- [A Transformer-based approach to Irony and Sarcasm detection](https://mlsanity.com/paper/1911.10401/) (2019)
- [The Role of Conversation Context for Sarcasm Detection in Online Interactions](https://mlsanity.com/paper/1707.06226/) (2017)
- [A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict](https://mlsanity.com/paper/2109.03587/) (2021)
- [On Sarcasm Detection with OpenAI GPT-based Models](https://mlsanity.com/paper/2312.04642/) (2023)
- [SEVADE: Self-Evolving Multi-Agent Analysis with Decoupled Evaluation for Hallucination-Resistant Irony Detection](https://mlsanity.com/paper/2508.06803/) (2025)

## Built on by (most cited first, 1 of 1)

- [GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification](https://mlsanity.com/paper/2604.08879/) (2026)

## Abstract (arXiv)

Sarcasm detection remains a significant challenge due to its reliance on nuanced contextual understanding, world knowledge, and multi-faceted linguistic cues that vary substantially across different sarcastic expressions. Existing approaches, from fine-tuned transformers to large language models, apply a uniform reasoning strategy to all inputs, struggling to address the diverse analytical demands of sarcasm. These demands range from modeling contextual expectation violations to requiring external knowledge grounding or recognizing specific rhetorical patterns. To address this limitation, we introduce RAM-SD, a Retrieval-Augmented Multi-Agent framework for Sarcasm Detection. The framework operates through four stages: (1) contextual retrieval grounds the query in both sarcastic and non-sarcastic exemplars; (2) a meta-planner classifies the sarcasm type and selects an optimal reasoning plan from a predefined set; (3) an ensemble of specialized agents performs complementary, multi-view analysis; and (4) an integrator synthesizes these analyses into a final, interpretable judgment with a natural language explanation. Evaluated on four standard benchmarks, RAM-SD achieves a state-of-the-art Macro-F1 of 77.74%, outperforming the strong GPT-4o+CoC baseline by 7.01 points. Our framework not only sets a new performance benchmark but also provides transparent and interpretable reasoning traces, illuminating the cognitive processes behind sarcasm comprehension.