RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training

• URL: http://arxiv.org/abs/2606.04272v1
• Date: Tue, 02 Jun 2026 22:55:18 GMT
• Title: RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training
• Abstract summary: We find that RL is effective very early, and often matches the full SFT$to$RL pipeline early as well.<n>Applying RL directly to base checkpoints expands the model's distribution.<n>The general capabilities of the model remain essentially unchanged by RL, while they degrade following SFT.
• Score: 18.932290080075685
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT). We question this status quo by training a LLM from scratch and applying RL, SFT, and SFT followed by RL directly to intermediate pre-training checkpoints. We find that RL is effective very early, and often matches the full SFT$\to$RL pipeline early as well. Through experiments on harder problems, we find that targeted pre-training data composition is a strong lever for RL effectiveness, even more so than model scale. Beyond reasoning accuracy, applying RL directly to base checkpoints expands the model's distribution; the sharpening effect reported in recent work arises only when RL follows SFT. The general capabilities of the model remain essentially unchanged by RL, while they degrade following SFT. Finally, we merge RL and SFT objectives by parallel averaging, which outperforms across all other training methods discussed, across metrics, while preserving general capabilities. Together, these results suggest that LLM training might benefit from an expanded use of RL.

Related papers

• Understanding Reasoning from Pretraining to Post-Training [53.890128750021375]
  We use chess as a controlled testbed for studying reasoning across the full pretraining-to-post-training pipeline.<n>We find that the post-RL performance at given RL compute level is well-predicted from the pretraining loss.<n>We further test whether our findings transfer beyond chess by training a 1B language model on math-domain text.
  arXiv  Detail & Related papers  (2026-07-17T16:31:58Z)
• Learning What to Learn: Stage-Specific Data Sets for SFT-then-RL in Small Language Model Reasoning [29.726247369977198]
  We argue that data strategy should be aligned with the distinct roles of SFT and RL.<n>We propose a difficulty-aware SFT-then-RL framework that organizes training data into stage-specific sets.
  arXiv  Detail & Related papers  (2026-06-03T05:25:06Z)
• SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models [51.99912169291891]
  Reinforcement learning (RL) has emerged as a promising paradigm for training reasoning-oriented models.<n>We propose a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL)<n>Our findings suggest that alternating between RL and IRL offers an effective pathway toward extending the exploration capacity of reasoning-oriented large language models.
  arXiv  Detail & Related papers  (2026-04-18T13:49:47Z)
• Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning [8.550698116833123]
  Post-training of reasoning LLMs typically consists of an offline SFT stage followed by an online reinforcement learning stage.<n>We show that, after identical RL training, models from stronger SFT checkpoints can significantly underperform those from weaker ones.<n>We propose PEAR, an SFT-stage method that corrects this mismatch and better prepares the model for RL.
  arXiv  Detail & Related papers  (2026-02-01T06:53:45Z)
• Not All Steps are Informative: On the Linearity of LLMs' RLVR Training [14.59942263367421]
  Reinforcement learning with verifiable rewards (RLVR) has become a central component of large language model (LLM) post-training.<n>We investigate whether future model states can be predicted from intermediate checkpoints via extrapolation, avoiding continued expensive training.<n>We show that Weight Extrapolation produces models with performance comparable to standard RL training while requiring significantly less computation.
  arXiv  Detail & Related papers  (2026-01-08T03:06:18Z)
• On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models [73.10315509190623]
  Recent reinforcement learning techniques have yielded impressive reasoning improvements in language models.<n>It remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during pre-training.<n>We develop a fully controlled experimental framework that isolates the causal contributions of pre-training, mid-training, and RL-based post-training.
  arXiv  Detail & Related papers  (2025-12-08T18:12:10Z)
• QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs [80.76334908639745]
  We propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs)<n>QeRL addresses issues by combining NVFP4 quantization with Low-Rank Adaptation (LoRA)<n>Experiments demonstrate that QeRL delivers over 1.5 times speedup in the rollout phase.
  arXiv  Detail & Related papers  (2025-10-13T17:55:09Z)
• Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead [20.446287312285648]
  We study whether high SFT scores translate to improved performance after RL.<n>We find high SFT scores can be biased toward simpler or more homogeneous data and are not reliably predictive of subsequent RL gains or scaled-up post-training effectiveness.<n>We study alternative metrics and identify generalization loss on held-out reasoning examples and Pass@large k performance to provide strong proxies for the RL outcome.
  arXiv  Detail & Related papers  (2025-10-02T02:57:00Z)
• Reinforcement Learning on Pre-Training Data [55.570379963147424]
  We introduce Reinforcement Learning on Pre-Training data (R), a new training-time scaling paradigm for optimizing large language models (LLMs)<n>R enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL)<n>Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of R.
  arXiv  Detail & Related papers  (2025-09-23T17:10:40Z)
• Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle [66.80133103857703]
  Reinforcement Learning (RL) has markedly enhanced the reasoning and alignment performance of Large Language Models (LLMs)<n>This survey aims to present researchers and practitioners with the latest developments and frontier trends at the intersection of RL and LLMs.
  arXiv  Detail & Related papers  (2025-09-20T13:11:28Z)
• Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning [93.00629872970364]
  Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks.<n>We introduce SPARKLE, a fine-grained analytic framework to dissect the effects of RL across three key dimensions.<n>We study whether difficult problems -- those yielding no RL signals and mixed-quality reasoning traces -- can still be effectively used for training.
  arXiv  Detail & Related papers  (2025-06-05T07:53:59Z)
• Teaching Large Language Models to Reason with Reinforcement Learning [38.17625148525193]
  Reinforcement Learning from Human Feedback (textbfRLHF) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from feedback.
  arXiv  Detail & Related papers  (2024-03-07T16:36:29Z)
• RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$ [12.111848705677142]
  We propose RL$3$, a hybrid approach that incorporates action-values, learned per task via traditional RL, in the inputs to Meta-RL.<n>We show that RL$3$ earns a greater cumulative reward in the long term compared to RL$2$ while drastically reducing meta-training time and generalizes better to out-of-distribution tasks.
  arXiv  Detail & Related papers  (2023-06-28T04:16:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.