Skip to content
← Back to explorer

SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning

Chenzhi Hu, Qinzhe Hu, Yuhang Xu, Junyi Chen, Ruijie Wang, Shengzhong Liu, Jianxin Li, Fan Wu, Guihai Chen · Mar 9, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 9, 2026, 6:08 AM

Recent

Extraction refreshed

Mar 13, 2026, 5:21 PM

Fresh

Extraction source

Persisted extraction

Confidence 0.45

Abstract

Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths. However, the inherent verbosity of these processes frequently results in redundancy and overthinking. To address this issue, existing works leverage Group Relative Policy Optimization (GRPO) to reduce LRM output length, but their static length reward design cannot dynamically adapt according to the relative problem difficulty and response length distribution, causing over-compression and compromised accuracy. Therefore, we propose SmartThinker, a novel GRPO-based efficient reasoning method with progressive CoT length calibration. SmartThinker makes a two-fold contribution: First, it dynamically estimates the optimal length with peak accuracy during training and guides overlong responses toward it to reduce response length while sustaining accuracy. Second, it dynamically modulates the length reward coefficient to avoid the unwarranted penalization of correct reasoning paths. Extensive experiment results show that SmartThinker achieves up to 52.5% average length compression with improved accuracy, and achieves up to 16.6% accuracy improvement on challenging benchmarks like AIME25. The source code can be found at https://github.com/SJTU-RTEAS/SmartThinker.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.45 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

15/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths.

Quality Controls

partial

Calibration

Confidence: Low Source: Persisted extraction evidenced

Calibration/adjudication style controls detected.

Evidence snippet: Therefore, we propose SmartThinker, a novel GRPO-based efficient reasoning method with progressive CoT length calibration.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths.

Reported Metrics

partial

Accuracy

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Coding
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Calibration
  • Confidence: 0.45
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

accuracy

Research Brief

Deterministic synthesis

Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths. HFEPX signals include Automatic Metrics with confidence 0.45. Updated from current HFEPX corpus.

Generated Mar 13, 2026, 5:21 PM · Grounded in abstract + metadata only

Key Takeaways

  • Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths.
  • Therefore, we propose SmartThinker, a novel GRPO-based efficient reasoning method with progressive CoT length calibration.
  • Extensive experiment results show that SmartThinker achieves up to 52.5% average length compression with improved accuracy, and achieves up to 16.6% accuracy improvement on…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (accuracy).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths.
  • Therefore, we propose SmartThinker, a novel GRPO-based efficient reasoning method with progressive CoT length calibration.
  • Extensive experiment results show that SmartThinker achieves up to 52.5% average length compression with improved accuracy, and achieves up to 16.6% accuracy improvement on challenging benchmarks like AIME25.

Why It Matters For Eval

  • Extensive experiment results show that SmartThinker achieves up to 52.5% average length compression with improved accuracy, and achieves up to 16.6% accuracy improvement on challenging benchmarks like AIME25.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Pass: Quality control reporting appears

    Detected: Calibration

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: accuracy

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote