7 papers
Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal
MichaÅ Wawer, JarosÅaw A. Chudziak
Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation. We argue that this objective is insuffi…
Who Decides What Is Harmful? Content Moderation Policy Through A Multi-Agent Personalised Inference Framework
Ewelina Gajewska, Michal Wawer, Katarzyna Budzynska +1
The increasing scale and complexity of online platforms raises critical policy questions around harmful content, digital well-being, and user autonomy. Traditional content moderati…
When AI Agents Disagree Like Humans: Reasoning Trace Analysis for Human-AI Collaborative Moderation
MichaÅ Wawer, JarosÅaw A. Chudziak
When LLM-based multi-agent systems disagree, current practice treats this as noise to be resolved through consensus. We propose it can be signal. We focus on hate speech moderation…
On Theoretically-Driven LLM Agents for Multi-Dimensional Discourse Analysis
Maciej Uberna, MichaÅ Wawer, JarosÅaw A. Chudziak +1
Identifying the strategic uses of reformulation in discourse remains a key challenge for computational argumentation. While LLMs can detect surface-level similarity, they often fai…
ElliottAgents: A Natural Language-Driven Multi-Agent System for Stock Market Analysis and Prediction
JarosÅaw A. Chudziak, MichaÅ Wawer
This paper presents ElliottAgents, a multi-agent system leveraging natural language processing (NLP) and large language models (LLMs) to analyze complex stock market data. The syst…
Leveraging a Multi-Agent LLM-Based System to Educate Teachers in Hate Incidents Management
Ewelina Gajewska, Michal Wawer, Katarzyna Budzynska +1
Computer-aided teacher training is a state-of-the-art method designed to enhance teachers' professional skills effectively while minimising concerns related to costs, time constrai…