One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows Paper • 2608.19741 • Published 5 days ago • 2
Enhance Reasoning by Learning from Mistakes: Peer-Review Knowledge Distillation from Multiple Large Language Models Paper • 2410.03663 • Published Oct 4, 2024
Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry Paper • 2601.22588 • Published Jan 30 • 6
Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry Paper • 2601.22588 • Published Jan 30 • 6