PhD student, Pennsylvania State University
2 papers at NeurIPS 2025
We introduce AgentTTS, an LLM-agent framework that efficiently allocates test-time compute across multi-stage tasks, achieving compute-optimal performance through insight-guided adaptive search.
We show that explicit reasoning via chain-of-thought can hurt instruction-following in LLMs by reducing constraint adherence, and propose four mitigation methods to recover or improve performance.
