Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention

ACL ARR 2026 January Submission1723 Authors

Keywords: Inference methods

Abstract: Recent progress in large language models (LLMs) has focused on test-time scaling to improve reasoning via increased inference computation, but often at the cost of efficiency. We revisit test-time behavior and uncover a simple yet underexplored phenomenon: reasoning uncertainty is highly localized—only a small subset of high-entropy tokens dominantly affects output correctness. Motivated by this, we propose Minimal Test-Time Intervention (MTI), a training-free framework that enhances reasoning accuracy and stability with minimal overhead. MTI includes: (i) Selective CFG intervention, applying classifier-free guidance only at uncertain positions; and (ii) Lightweight negative-prompt guidance, reusing the main model’s KV cache to approximate unconditional decoding efficiently. MTI yields consistent gains across general, coding, and STEM tasks—e.g., +9.28\% average improvement on six benchmarks for DeepSeek-R1-7B and +11.25\% on AIME2024 using Ling-mini-2.0—while remaining highly efficient.

Paper Type: Long

Research Area: Language Models

Research Area Keywords: Generation

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 1723