5 papers
Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation
Ante Kapetanovic, Tomislav Duricic, Andro Mercep +1
Large language models (LLMs) are increasingly used as rerankers in conversational recommender systems, yet measured gains depend strongly on the retrieval and inference protocol. O…
A Phased Workflow for Operating LLM-Based Coding Agents
Ante Kapetanovic, Tomislav Duricic, Andro Mercep +1
LLM-based coding agents combine a foundation model with a harness that shapes agent behavior. For non-trivial tasks, how practitioners structure their work with the coding agents d…
Conversational Recommendation over Live E-Commerce Catalogues with Self-Refreshing Retrieval
Ante Kapetanovic, Tomislav Duricic, Dionizije Fa +2
Conversational recommender systems based on large language models (LLMs) are usually evaluated on static, pre-indexed item collections, yet e-commerce catalogues change continuousl…
Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence
Ante Kapetanovic, Kemal Altwlkany, Andro Mercep +2
Large language models (LLMs) increasingly assess generated content, giving rise to the LLM-as-a-Judge paradigm. These systems now score outputs, filter content, and gate iterative…
Robocalls: A Worldwide or US-only Problem? Analyzing Spam and Fraud in International Phone Calls
Kemal Altwlkany, Andro Merćep, Tomislav Đuričić +2
Unsolicited automated phone calls (robocalls) are a serious threat: in the US alone, these calls resulted in reported losses of 1.1$ billion during 2025. Phishing and spoofing cons…