ARTFEED — Contemporary Art Intelligence

Universal Reasoner: A Plug-and-Play Reasoning Module for Frozen LLMs

ai-technology · 2026-05-22

Researchers propose Universal Reasoner (UniR), a modular reasoning module that can be added to frozen large language models (LLMs) without retraining. UniR decomposes reward signals into token-level guidance, enabling specialized reasoning while preserving generalization. It uses verifiable rewards and a decoupled training approach, then combines with frozen LLMs at inference by adding output logits. This addresses the high cost and architectural dependencies of traditional fine-tuning methods.

Key facts

  • UniR is a modular, composable, plug-and-play reasoning module.
  • It works with frozen LLMs without retraining.
  • Reward is decomposed into token-level guidance.
  • Training is decoupled using verifiable rewards.
  • At inference, UniR adds its output logits to the frozen LLM.
  • Parameter-Efficient Fine-Tuning (PEFT) methods require retraining per backbone.
  • UniR aims to enhance reasoning without compromising generalization.
  • The approach reduces computational resource demands.

Entities

Sources