2 papers
cs.LG2026
Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts
Saloni Garg, Amit Sagtani
Efficient routing across multiple LLMs enables cost-quality tradeoffs by directing queries to the cheapest capable model. Prior work attributes routing headroom to an "unsolvabilit…
cs.LG2024
Enhancing LLMs for Physics Problem-Solving using Reinforcement Learning with Human-AI Feedback
Avinash Anand, Kritarth Prasad, Chhavi Kirtani +6
Large Language Models (LLMs) have demonstrated strong capabilities in text-based tasks but struggle with the complex reasoning required for physics problems, particularly in advanc…