mlsanityData to 7 Oct 2026

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

arXiv 2603.08251 ↗First posted 9 Mar 2026cs.CLcited by 13

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (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.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 36 of its 47 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

36 of 47 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMs17 Feb
  2. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs30 Dec
  3. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug
  4. 2024Large Language Models have Intrinsic Self-Correction Ability21 Jun
  5. 2023Large Language Models Cannot Self-Correct Reasoning Yet3 Oct
  6. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 30

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  8. 2023Let's Verify Step by Stepcited by 3,598
  9. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  10. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,057
  11. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 895
  12. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
18 more
  1. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 701
  2. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 231
  3. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  4. 2020The Right Tool for the Job: Matching Model and Instance Complexitiescited by 125
  5. 2024Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervisioncited by 95
  6. 2025OverThink: Slowdown Attacks on Reasoning LLMscited by 94
  7. 2024LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Playcited by 65
  8. 2024Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Modelscited by 47
  9. 2024MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoningcited by 40
  10. 2024Learning to Refine with Fine-Grained Natural Language Feedbackcited by 27
  11. 2026Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoringcited by 21
  12. 2026PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoningcited by 19
  13. 2026Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perceptioncited by 17
  14. 2024What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoningcited by 14
  15. 2025Token-Importance Guided Direct Preference Optimizationcited by 14
  16. 2024Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Modelscited by 5
  17. 2025A Large Language Model-Enhanced Q-learning for Capacitated Vehicle Routing Problem with Time Windowscited by 3
  18. 2025Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compressioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

By area:

  1. 2026PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learningcited by 10
  2. 2026CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registrationcited by 9
  3. 2026PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inferencecited by 6
  4. 2026IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registrationcited by 5
  5. 2026Robust Regularized Policy Iteration under Transition Uncertaintycited by 2
  6. 2026CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoningcited by 2
  7. 2026FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Modelscited by 2
  8. 2026SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineeringcited by 2
  9. 2026SF-AMS: Strategic Forgetting for Structured Memory in LLM Agentcited by 1
  10. 2026Controllable Singing Style Conversion with Boundary-Aware Information Bottleneckcited by 0
  11. 2026Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completioncited by 0
  12. 2026SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Modelscited by 0
1 more
  1. 2026Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
  2. 2025Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
  3. 2026Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning
  4. 2026CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute
  5. 2026Divergent-Convergent Reasoning: Scaling Test-Time Compute through Structured Solution Synthesis
  6. 2025Learning to Ponder: Adaptive Reasoning in Latent Space
  7. 2025Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models
  8. 2026BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning