Multi-Agent Reasoning with Adaptive Worker Allocation for Stance Detection
Meysam Sabbaghan, Arman Zareian Jahromi, Doina Caragea
Why It Matters
What makes this one worth your time
This approach could improve the robustness and accuracy of stance detection in complex and nuanced text, which is crucial for applications like sentiment analysis and opinion mining.
A novel multi-agent framework enhances stance detection by focusing on reasoning-level synthesis.
Summary
The paper introduces a multi-agent reasoning framework for stance detection that uses a Manager-Worker architecture to adaptively allocate workers based on input complexity. Each worker provides reasoning-only explanations, which the manager synthesizes to make a final prediction. The framework is evaluated on several datasets, showing improved performance on implicit and context-dependent stance cases.
Key contributions
- Introduction of a multi-agent reasoning framework for stance detection.
- Adaptive worker allocation strategy based on input complexity.
- Demonstrated improvements on implicit and context-dependent stance cases.
Notable insights
- Adaptive worker allocation based on input complexity allows for more nuanced analysis.
- Reasoning-level synthesis rather than label-level voting enhances interpretability and robustness.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2606.11609v1 Announce Type: new Abstract: Stance detection requires identifying an author's position toward a target, often from short-form texts where stance is implicit, indirect, or rhetorically framed. Although large language models (LLMs) achieve strong performance on this task, single-pass prompting can be brittle when multiple interpretations are plausible. Existing aggregation strategies, such as majority voting or self-consistency, improve robustness by combining labels, but they discard the intermediate reasoning needed to resolve conflicting interpretations. We introduce a multi-agent reasoning framework with adaptive worker allocation for stance detection that shifts aggregation from label-level voting to reasoning-level synthesis. The framework employs a Manager-Worker architecture in which a Manager adaptively allocates a variable number of Worker agents based on input complexity. Each Worker analyzes the input from a distinct perspective and produces a reasoning-only explanation without emitting a stance label; the Manager then synthesizes these explanations to produce the final prediction. We evaluate the proposed framework on SemEval-2016, P-Stance, and COVID-19 Stance using Llama, Mistral, and Gemini. Results show that the framework yields the largest gains on implicit and context-dependent stance cases, achieving 86.07 Macro-F1 on COVID-19 and 82.90 on SemEval-2016, while remaining competitive on more explicit stance datasets such as P-Stance. These findings suggest that adaptive reasoning-level aggregation is most beneficial when stance cannot be reliably inferred from surface cues alone.