2 papers
cs.AI2026
Unlocking LLM Creativity in Science through Analogical Reasoning
Andrew Shen, Shaul Druckmann, James Zou
Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that can consistently generate novel…
cs.LG2025
Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning
Feng Chen, Allan Raventos, Nan Cheng +2
Recent progress in large language models (LLMs) highlights the power of scaling test-time compute to achieve strong performance on complex tasks, such as mathematical reasoning and…