SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914489503318016 |
|---|---|
| author | Wang, Xuan Ming, Yu Zhong, Xinhao Yu, Xinyu Wang, Wenjie Chen, Shuai Lin, Wei |
| author_facet | Wang, Xuan Ming, Yu Zhong, Xinhao Yu, Xinyu Wang, Wenjie Chen, Shuai Lin, Wei |
| contents | Large Language Models (LLMs) are prone to logical hallucinations and stochastic drifts during long-chain reasoning. While Classifier-Free Guidance (CFG) can improve instruction adherence, standard static implementations often cause semantic dilution and linguistic degradation. We propose SPREG (Structured Plan-guided Real-time Entropy Gating), a lightweight inference-time framework for surgical error rectification. SPREG employs an adaptive dual-threshold mechanism to monitor real-time entropy, identifying sudden ``entropy spikes'' as reliable indicators of logical failure. Upon detection, it triggers a dynamic repair by replacing uninformative null-priors with reference distributions synthesized from historical high-confidence states. By modulating guidance intensity according to structured reasoning stages (e.g., Action, Observation), SPREG steers the model back to a stable manifold without compromising fluency. Our experiments demonstrate significant gains, notably a 20.0% absolute accuracy improvement on AIME25, while effectively suppressing uncontrolled entropy drift in complex tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17884 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning Wang, Xuan Ming, Yu Zhong, Xinhao Yu, Xinyu Wang, Wenjie Chen, Shuai Lin, Wei Artificial Intelligence Large Language Models (LLMs) are prone to logical hallucinations and stochastic drifts during long-chain reasoning. While Classifier-Free Guidance (CFG) can improve instruction adherence, standard static implementations often cause semantic dilution and linguistic degradation. We propose SPREG (Structured Plan-guided Real-time Entropy Gating), a lightweight inference-time framework for surgical error rectification. SPREG employs an adaptive dual-threshold mechanism to monitor real-time entropy, identifying sudden ``entropy spikes'' as reliable indicators of logical failure. Upon detection, it triggers a dynamic repair by replacing uninformative null-priors with reference distributions synthesized from historical high-confidence states. By modulating guidance intensity according to structured reasoning stages (e.g., Action, Observation), SPREG steers the model back to a stable manifold without compromising fluency. Our experiments demonstrate significant gains, notably a 20.0% absolute accuracy improvement on AIME25, while effectively suppressing uncontrolled entropy drift in complex tasks. |
| title | SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.17884 |