Research

Paper

AI LLM March 09, 2026

Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement

Authors

Dongxu Zhang, Hongqiang Lin, Yiding Sun, Pengyu Wang, Qirui Wang, Ning Yang, Jihua Zhu

Abstract

Scaling test-time computation enhances LLM reasoning ability but faces a uniform computation paradox. Allocating identical resources leads to over-correction on simple tasks and insufficient refinement on complex ones. To address this, we propose CoFiCot, a coarse-to-fine adaptive framework that dynamically tailors inference strategies to problem difficulty. Specifically, we implement a multi-metric classifier that triages queries by synthesizing semantic entropy, consensus reliability, and predicted reasoning depth . This enables a differentiated refinement stage that applies efficient aggregation for simple queries while routing complex ones to a context-aware correction loop . We formalize correction as a stateful sequential propagation process , where each repair is strictly conditioned on the verified history of prior rectifications. By integrating Process Reward Models (PRMs) within this state-dependent trajectory, CoFiCot effectively bridges the gap between granular error localization and global logical coherence, preventing the context fragmentation typical of stateless refinement methods.

Metadata

arXiv ID: 2603.08251
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-09
Fetched: 2026-03-10 05:43

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.08251v1</id>\n    <title>Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement</title>\n    <updated>2026-03-09T11:23:07Z</updated>\n    <link href='https://arxiv.org/abs/2603.08251v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.08251v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Scaling test-time computation enhances LLM reasoning ability but faces a uniform computation paradox. Allocating identical resources leads to over-correction on simple tasks and insufficient refinement on complex ones. To address this, we propose CoFiCot, a coarse-to-fine adaptive framework that dynamically tailors inference strategies to problem difficulty. Specifically, we implement a multi-metric classifier that triages queries by synthesizing semantic entropy, consensus reliability, and predicted reasoning depth . This enables a differentiated refinement stage that applies efficient aggregation for simple queries while routing complex ones to a context-aware correction loop . We formalize correction as a stateful sequential propagation process , where each repair is strictly conditioned on the verified history of prior rectifications. By integrating Process Reward Models (PRMs) within this state-dependent trajectory, CoFiCot effectively bridges the gap between granular error localization and global logical coherence, preventing the context fragmentation typical of stateless refinement methods.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-09T11:23:07Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Dongxu Zhang</name>\n    </author>\n    <author>\n      <name>Hongqiang Lin</name>\n    </author>\n    <author>\n      <name>Yiding Sun</name>\n    </author>\n    <author>\n      <name>Pengyu Wang</name>\n    </author>\n    <author>\n      <name>Qirui Wang</name>\n    </author>\n    <author>\n      <name>Ning Yang</name>\n    </author>\n    <author>\n      <name>Jihua Zhu</name>\n    </author>\n  </entry>"
}