# ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools -- From Consensus Learning to Ambiguity-Driven Emotion Reasoning

arXiv: https://arxiv.org/abs/2602.12714 · HTML: https://mlsanity.com/paper/2602.12714/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 56 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)
- 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, 25 of 25)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation](https://mlsanity.com/paper/2312.15185/) (2023)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning](https://mlsanity.com/paper/2406.11161/) (2024)
- [WavLLM: Towards Robust and Adaptive Speech Large Language Model](https://mlsanity.com/paper/2404.00656/) (2024)
- [AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models](https://mlsanity.com/paper/2501.16566/) (2025)
- [BLSP-Emo: Towards Empathetic Large Speech-Language Models](https://mlsanity.com/paper/2406.03872/) (2024)
- [EmoLLM: Multimodal Emotional Understanding Meets Large Language Models](https://mlsanity.com/paper/2406.16442/) (2024)
- [Don't Waste a Single Annotation: Improving Single-Label Classifiers Through Soft Labels](https://mlsanity.com/paper/2311.05265/) (2023)
- [The Ambiguous World of Emotion Representation](https://mlsanity.com/paper/1909.00360/) (2019)
- [The MSP-Podcast Corpus](https://mlsanity.com/paper/2509.09791/) (2025)
- [AffectGPT-R1: Leveraging Reinforcement Learning for Open-Vocabulary Multimodal Emotion Recognition](https://mlsanity.com/paper/2508.01318/) (2025)
- [Rethinking Emotion Annotations in the Era of Large Language Models](https://mlsanity.com/paper/2412.07906/) (2024)
- [EMO-RL: Emotion-Rule-Based Reinforcement Learning Enhanced Audio-Language Model for Generalized Speech Emotion Recognition](https://mlsanity.com/paper/2509.15654/) (2025)
- [EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition](https://mlsanity.com/paper/2508.14130/) (2025)
- [More Similar than Dissimilar: Modeling Annotators for Cross-Corpus Speech Emotion Recognition](https://mlsanity.com/paper/2509.12295/) (2025)
- [Reasoning Beyond Majority Vote: An Explainable SpeechLM Framework for Speech Emotion Recognition](https://mlsanity.com/paper/2509.24187/) (2025)
- [Revisiting Modeling and Evaluation Approaches in Speech Emotion Recognition: Considering Subjectivity of Annotators and Ambiguity of Emotions](https://mlsanity.com/paper/2510.05934/) (2025)

## Abstract (arXiv)

Speech Large Language Models (SLLMs) enable high-level emotion reasoning but often produce ungrounded, text-biased judgments without verifiable acoustic evidence. In contrast, self-supervised speech encoders such as WavLM provide strong acoustic representations yet remain opaque discriminative models with limited interpretability. To bridge this gap, we introduce ADEPT (Agentic Decoding of Emotion via Evidence Probing Tools), a framework that reframes emotion recognition as a multi-turn inquiry process rather than a single-pass prediction. ADEPT transforms an SLLM into an agent that maintains an evolving candidate emotion set and adaptively invokes dedicated semantic and acoustic probing tools within a structured pipeline of candidate generation, evidence collection, and adjudication. Crucially, ADEPT enables a paradigm shift from consensus learning to ambiguity-driven emotion reasoning. Since human affect exhibits inherent complexity and frequent co-occurrence of emotions, we treat minority annotations as informative perceptual signals rather than discarding them as noise. Finally, we integrate Group Relative Policy Optimization (GRPO) with an Evidence Trust Gate to explicitly couple tool-usage behaviors with prediction quality and enforce evidence-grounded reasoning. Experiments show that ADEPT improves primary emotion accuracy in most settings while substantially improving minor emotion characterization, producing explanations grounded in auditable acoustic and semantic evidence.