mlsanityData to 14 Oct 2026

Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?

arXiv 2506.19733 ↗First posted 24 Jun 2025cs.CLcited by 2

On the map: LLM reasoning → Reinforcement learning for reasoning

Abstract (arXiv)

Reinforcement post training (RPT) has recently shown promise in improving the reasoning abilities of large language models (LLMs). However, it remains unclear how well these improvements generalize to new domains, as prior work evaluates RPT models on data from the same domains used for post-training. To understand the generalizability of RPT, we conduct two studies with specific focus on Reinforcement Learning with Verifiable Rewards (RLVR). (1) Observational: we compare a wide range of open-weight RPT models against their corresponding base models across multiple domains, including both seen and unseen domains in their fine-tuning data. (2) Interventional: we fine-tune LLMs with RPT on single domains and evaluate their performance across multiple domains. Both studies converge on the same conclusion that, although RPT brings substantial gains on tasks similar to the fine-tuning data, the gains generalize inconsistently and can vanish on domains with different reasoning patterns.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. First posted on arXiv 24 Jun 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalizationcited by 7
  2. 2025Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspectivecited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2025Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead
  2. 2025On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
  3. 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
  4. 2026Demystifying Reinforcement Learning Post-Training of Language Models
  5. 2026To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models
  6. 2025RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs
  7. 2025Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle
  8. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?