MirrorBench: An Extensible Framework to Evaluate User-Proxy Agents for Human-Likeness Paper • 2601.08118 • Published Jan 13 • 2
Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs Paper • 2512.07525 • Published Dec 8, 2025 • 60
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning Paper • 2512.07461 • Published Dec 8, 2025 • 79
Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky Paper • 2507.03336 • Published Jul 4, 2025 • 7
