Peer-reviewed

Publications

• ICLR 2026LLM Reasoning Workshop
  Evaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy Bogdanov I., Manakina O., Lung C.H.
• NeurIPS 2025MTI-LLM Workshop
  Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs Manakina O., Bogdanov I., Lung C.H.
• AIED 2025Main track
  Prompts Eliciting Active and Constructive Engagement Improve Learning Across Traditional and LLM Contexts Manakina O., Muldner K.
• COMPSAC 2025IEEE · QUORS Workshop
  Designing Reusable LLM-Enhanced Assignments: A Quality-Oriented Framework for Software Engineering Education Manakina O., Lung C.H.
• EDM 2025WLIEDM Workshop
  Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring Manakina O., Bogdanov I.