From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916060157968384 |
|---|---|
| author | Wang, Shaojie Zhang, Liang |
| author_facet | Wang, Shaojie Zhang, Liang |
| contents | Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcement Learning (RL). While effective, a closer examination reveals a fundamental gap: this approach does not align with how humans actually solve problems. Human cognition naturally decomposes problem-solving into two distinct stages: first acquiring abstract strategies (i.e., meta-knowledge) that generalize across problems, then adapting them to specific instances. In contrast, by treating complete trajectories as basic units, current methods are inherently problem-centric, entangling abstract strategies with problem-specific execution. To address this misalignment, we propose a cognitively-inspired framework that explicitly mirrors the two-stage human cognitive process. Specifically, Chain-of-Meta-Thought CoMT focuses supervised learning on abstract reasoning patterns without specific executions, enabling acquisition of generalizable strategies. Confidence-Calibrated Reinforcement Learning (CCRL) then optimizes task adaptation via confidence-aware rewards on intermediate steps, preventing overconfident errors from cascading and improving execution reliability. Experiments across four models and ten benchmarks show 2.10% and 3.86% improvements in-distribution and out-of-distribution respectively over standard methods, while remaining highly robust to variations in teacher model selection, optimization methods, and symbolic perturbations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21909 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning Wang, Shaojie Zhang, Liang Artificial Intelligence Computation and Language Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcement Learning (RL). While effective, a closer examination reveals a fundamental gap: this approach does not align with how humans actually solve problems. Human cognition naturally decomposes problem-solving into two distinct stages: first acquiring abstract strategies (i.e., meta-knowledge) that generalize across problems, then adapting them to specific instances. In contrast, by treating complete trajectories as basic units, current methods are inherently problem-centric, entangling abstract strategies with problem-specific execution. To address this misalignment, we propose a cognitively-inspired framework that explicitly mirrors the two-stage human cognitive process. Specifically, Chain-of-Meta-Thought CoMT focuses supervised learning on abstract reasoning patterns without specific executions, enabling acquisition of generalizable strategies. Confidence-Calibrated Reinforcement Learning (CCRL) then optimizes task adaptation via confidence-aware rewards on intermediate steps, preventing overconfident errors from cascading and improving execution reliability. Experiments across four models and ten benchmarks show 2.10% and 3.86% improvements in-distribution and out-of-distribution respectively over standard methods, while remaining highly robust to variations in teacher model selection, optimization methods, and symbolic perturbations. |
| title | From Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2601.21909 |