ThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning Models

Key points

• Small reasoning models (SRMs) have shown strong performance on complex reasoning tasks by generating extended chain-of-thought trajectories, but they often fail to recover once their reasoning enters an erroneous path.1
• Existing test-time fusion methods rely on local fusion signals to determine when to trigger fusion, which can be misled by transient uncertainty fluctuations and may reinforce unstable reasoning trajectories.1
• ThinkFuse compares segment-level uncertainty shifts with trajectory-level uncertainty trends to identify unstable reasoning points and fuse auxiliary reasoning paths into the primary model's trajectory.1
• Our analysis shows that ThinkFuse requires fewer fusion triggers and generates fewer tokens, highlighting the efficiency of selective triggering.1

Sources (1)

• [1]ThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning Models
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 05:56 AM

  We propose ThinkFuse, a training-free test-time fusion framework that selectively intervenes in unreliable reasoning segments.

  Small reasoning models (SRMs) have shown strong performance on complex reasoning tasks by generating extended chain-of-thought trajectories, but they often fail to recover once their reasoning enters an erroneous path.

Extractive summary: sentences quoted from the sources.