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

2026-03-09 · Dongxu Zhang, Hongqiang Lin, Yiding Sun, Pengyu Wang, Qirui Wang, Ning Yang, Jihua Zhu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.08251

Code (0)

등록된 구현이 없습니다.

IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation

2026-06-23 · Zixuan Li, Haokun Lin, Yicheng Xiao, Zhiwei Li 외 arxiv

Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware prompt following, where object counts, spatial relations, attribute binding…

Text-to-Image Generation Visual Reasoning

Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures

2025-02-07 · Tushar Pandey, Ara Ghukasyan, Oktay Goktas, Santosh Kumar Radha

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet their performance is highly dependent on the prompting strategy and model scale. While reinforcement learning and fine-tuning have bee…

Mathematical Problem-Solving reinforcement-learning Reinforcement Learning

CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models

2026-07-01 · Qizhi Jiang, Shuo Wang, Pei Ke, Yuhang Song 외 arxiv

Large Reasoning Models (LRMs) have achieved remarkable success on complex tasks by leveraging long chain-of-thought (CoT) trajectories, yet they frequently exhibit overthinking on simple queries, resulting in significant…

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

2025-05-17 · Chenwei Lou, Zewei Sun, Xinnian Liang, Meng Qu 외

Large Language Models (LLMs) have demonstrated remarkable capabilities but often face challenges with tasks requiring sophisticated reasoning. While Chain-of-Thought (CoT) prompting significantly enhances reasoning, it i…

Reinforcement Learning (RL)

SpatialReasoner: Active Perception for Large-Scale 3D Scene Understanding

2025-12-02 · Hongpei Zheng, Shijie Li, Yanran Li, Hujun Yin arxiv

Spatial reasoning in large-scale 3D environments remains challenging for current vision-language models, which are typically constrained to room-scale scenarios. We introduce H$^2$U3D (Holistic House Understanding in 3D)…

Visual Question Answering Reinforcement Learning Scene Understanding Spatial Reasoning