Extent of new versus repurposed reasoning capabilities in thinking language models

Determine to what extent thinking language models learn entirely new reasoning capabilities during post-training versus repurpose pre-existing capabilities and representations already present in their base models acquired during pre-training, in order to explain their superior performance on reasoning tasks.

Background

The paper examines why reasoning-focused ("thinking") LLMs outperform their base counterparts on benchmarks such as GSM8K and MATH500. It proposes evidence that base models already possess many reasoning mechanisms and that post-training (e.g., RLVR) primarily teaches when to deploy them. This question—new capability acquisition versus repurposing existing ones—frames the central contribution, motivating an unsupervised taxonomy of reasoning mechanisms and a hybrid steering approach to activate latent reasoning behaviors in base models.

Clarifying this distinction has practical implications for training efficiency and interpretability. If thinking models mostly learn orchestration rather than novel mechanisms, future methods might target activation-space interventions or timing policies, reducing reliance on extensive fine-tuning.

References

Despite consistent performance gains, it remains unclear to what extent thinking models learn entirely new reasoning capabilities or repurpose pre-existing base model ones.

— Base Models Know How to Reason, Thinking Models Learn When  (2510.07364 - Venhoff et al., 8 Oct 2025) in Abstract (p. 1)

Whether this reflects reusable reasoning, more reliable use of pretrained capabilities, or answer-format adaptation remains unresolved.

— Does Learning Protein Folding Generalize to Broader Reasoning?  (2609.38879 - Liu et al., 30 Sep 2026) in Section 6, Discussion and Conclusion

Whether heavier RL truly moves beyond elicitation remains open, and base-anchored diagnostics like Sharpening Tax offer a direct way to check it as post-training continues to scale.

— Sharpening Tax in Post-Training  (2610.01509 - Oh et al., 1 Oct 2026) in Section Discussion and Conclusion

Whether RLVR develops capabilities or makes existing ones easier to elicit remains open.

— Same Reward, Different Skills: When Multimodal RL Learns to Look  (2610.01908 - Ye et al., 1 Oct 2026) in Section 1, Introduction