Skip to content

Author

Jelena Mitrović

University of Belgrade, University of Passau

We have 8 of 56 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

AutoSim: A Self-Improving User Simulator for Conversational Search Evaluation

User simulators promise to evaluate conversational search systems at a scale human studies cannot reach, but only if their behavior is realistic enough to trust. We study AutoSim, a conversational-search user simulator whose relevance judgments rank a controlled pool of retrieval systems in agreement with NIST across t...

S. Zerhoudi, Jelena Mitrović, M. Granitzer · 1 citation
Preprint Oct 2026

Getting a Grip: Operating Human-Agent Software Teams Through Governed Messages

Software is increasingly developed by teams in which several people direct many coding agents from different vendors. Such teams must establish who may request what from whom, which messages start work, which decisions bind, and who caused a change. We propose to govern a human-agent team through its message protocol a...

Michael Granitzer, Kanishka Ghosh Dastidar, Andreas Einwiller et al. · 0 citations
Preprint Oct 2026

Faithful Query Resolution for Conversational Search

This paper compares five query-generation configurations within a behavior-adaptive assistant using BM25 and SPLADE retrieval, and finds that the weighted configuration obtains the highest mean retrieval scores, but this retrieval advantage does not coincide with the highest conversational satisfaction scores.

S. Zerhoudi, Ivica Kostric, Jelena Mitrović · 0 citations
Preprint Aug 2026

When Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale

This work evaluates eight representative chunking strategies across two scalable corpora, three embedding models, and multiple corpus sizes, measuring both retrieval effectiveness and system-level costs and shows that computationally expensive methods rarely provide consistent gains over simpler chunking.

Laura Caspari, K. G. Dastidar, M. Dinzinger et al. · 0 citations
Preprint Aug 2026

The Compaction Cliff in Long-Running AI Agent Memory

Knowledge Triage, a framework that classifies each line of an agent's knowledge base by type and routes each type through its own retention policy, is addressed, and AgentArtifactCorpus, the classifier, and the reference implementation are released.

S. Zerhoudi, Jelena Mitrović, M. Granitzer · 2 citations
Book Open access Jul 2026

Query Performance Prediction under Corpus Growth in Dense Retrieval

This work extends the QPP paradigm by studying query performance degradation under corpus inflation in dense retrieval systems and proposes simple adaptations to established QPP measures, most notably a top-k vs background Wasserstein distance measure, which yield more consistent associations with degradation and outpe...

Kanishka Ghosh Dastidar, M. Dinzinger, Laura Caspari et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.