Tag
This paper introduces Deep Reasoning, an inference-time approach that uses structured meta-reasoning to construct task-specific scaffolds for general-purpose agents. The proposed agent, Dolores, outperforms existing methods by distributing cognition across lower-load reasoning threads, reducing hallucinations and improving performance across multiple benchmarks.
This paper introduces CLIPer, a method for personalizing LLM outputs at inference time using a classifier, avoiding the computational cost of extensive fine-tuning.