LABBench2: An Improved Benchmark for AI Systems Performing Biology Research Many-Tier Instruction Hierarchy in LLM Agents Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series TInR: Exploring Tool-Internalized Reasoning in Large Language Models Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition