Emine Yilmaz

Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the contexts of multi-turn search agents are lengthy and complex. For example, the retrieved set of documents in each turn would...

Large Language Model (LLM)-based Multi-Agent Systems (MAS) enable complex problem-solving but introduce significant debugging challenges, characterized by long interaction traces, inter-agent dependencies, and delayed error manifestation. Existing diagnostic approaches often rely on expensive exp...

Large language models (LLMs) increasingly act as tool-using agents , and existing methods for evaluating and optimizing tool usage by LLMs typically assume a static tool environment with fixed APIs and documentation. In practice, toolsets evolve as tools are added, changed, or deprecated, introdu...